**Overview** We are a fast-growing SaaS company with a lean engineering team (~10 devs) utilizing a modern Python (FastAPI/Django) and Node.js backend, React frontend, and PostgreSQL stack. We have already deployed an initial multi-model agent stack—Claude Code, LiteLLM gateway, Git worktrees, and MCP integrations. We need an expert to run an intensive architecture review and optimization session for our current infrastructure. We are not looking for someone to build a full-time, weeks-long project from scratch. Instead, we need a seasoned engineer who has shipped this exact type of infrastructure end-to-end to audit our setup, identify architectural gaps, and guide our team on hardened implementation. This project must move fast. If your timeline is measured in weeks, please do not apply. We want someone who looks at this scope, jumps into a review session, and delivers actionable architectural guidance in days. This starts as a focused, urgent consultation. However, we expect ongoing advisory work—follow-ups, architecture adjustments, and enhancement reviews—as the AI tooling landscape shifts. For the right engineer, this will turn into a recurring relationship. We are completely open to a fixed price per milestone or an hourly structure. **What You Need to Have Actually Shipped and Can Review (Not Just Read About)** * **Full Agentic Coding Harnesses:** The entire loop: orchestrator → subagent → CI gate → merge loops. * **Isolation Layers:** Configured execution layers (such as E2B, Modal, or secure Docker runtimes) as isolated sandboxes for AI-generated code. * **Parallel Claude Code Sessions:** Managed multiple simultaneous subagents on scoped tasks via Git worktrees. * **Self-Hosted LiteLLM Gateways:** Routing to multiple models (Claude, GPT, Gemini, DeepSeek). * **MCP Server Infrastructure:** Connected file system, PostgreSQL, Atlassian, and Slack tool layers for active agents. * **Agent Framework Structures:** Used CLAUDE.md, COMMON\_MISTAKES.md, subagent role definitions, hook scripts, and settings.json. * **Human-in-the-Loop Orchestration:** Built Plan Mode or equivalent approval gates before agent execution. * **Multi-Agent Frameworks:** 7-agent feature factory patterns or frameworks like LangGraph, CrewAI, or Autogen. * **Durable Workflow Engines:** Applied Temporal, n8n, or similar tools for long-running agent workflow execution. * **Mechanical Quality Gates:** Treating CI green as the ultimate gate for agent output quality. \[[1](https://manveerc.substack.com/p/ai-agent-sandboxing-guide)\] **Our Current Stack (What you are reviewing)** * **Backend:** Python (FastAPI / Django) & Node.js (TypeScript) * **Frontend:** React (Next.js) * **Database & ORM:** PostgreSQL / Prisma / SQLAlchemy * **Infrastructure:** Docker Compose, AWS (ECS/EKS) * **CI/CD:** GitHub Actions / GitLab CI * **AI Layer:** Claude Code with shared `.claude/` directory, CLAUDE.md, and LiteLLM gateway in Docker * **MCP:** Atlassian (Jira/Confluence), custom PostgreSQL MCP server, Slack * **Workflow Automation:** Temporal / n8n * **QA Automation:** Playwright / Autonoma **Scope of Work (Review & Advisory Only)** 1. **Comprehensive Audit:** Audit our current agent harness and identify architectural gaps against a production-grade standard. 2. **Sandbox Strategy Consultation:** Review our environment strategy to ensure highly secure, isolated execution runtimes for agent code runs. 3. **Workflow Hardening Review:** Evaluate our parallel agent workflow setup (Git worktrees, subagent role configs, hook scripts, and settings lockdown). 4. **CI Pipeline Integration Strategy:** Advise on wiring our sandbox execution layer into the existing CI pipeline so agent-executed code runs in clean snapshots, not live infra. 5. **Architectural Runbook:** Deliver an optimization report / documented standard that our backend lead can easily own and execute going forward. **How to Apply** Skip the generic pitch. Show us something real to be considered: 1. A GitHub repo, architecture diagram, or Loom walkthrough of an agentic harness you have actually shipped. 2. Specific tools from our stack you have personally configured (E2B, LiteLLM, Claude Code, etc.). 3. One sentence explaining the hardest problem you solved to get full agent loops running reliably. 4. Your availability to conduct this high-impact architectural review session this week.

We are seeking an experienced AI practitioner and facilitator to deliver a highly interactive 4-hour "AI Champions" workshop for approximately 25 employees at a pharmaceutical company in Irvine, California. The ideal candidate will have strong expertise in Generative AI and practical experience applying AI within pharmaceutical, biotech, life sciences, clinical, quality, regulatory, or drug development environments. This is not a technical coding course. The objective is to help participants identify, evaluate, and champion practical AI use cases across business functions while understanding governance, compliance, and implementation considerations. Delivery Details Format: Onsite, instructor-led workshop Duration: 4 Hours Location: Irvine, California Timing: Q3 2026 Audience Size: Approximately 25 participants Audience Experience Level: Mixed experience levels Most participants are light users of ChatGPT and Microsoft Copilot Workshop Objectives The facilitator should be able to demonstrate practical AI applications and guide participants through identifying opportunities within their own departments. Potential topics include: Generative AI fundamentals and current landscape Prompt engineering and responsible AI usage Pharmaceutical and life sciences AI use cases Product development and research applications Clinical trial and patient screening opportunities Quality management and compliance use cases Regulatory and documentation support Manufacturing and operational excellence AI adoption strategies and change management Governance, risk, and compliance considerations The session should include interactive exercises, discussion, and department-specific use case exploration. Required Qualifications Experience delivering AI workshops or corporate training Strong knowledge of ChatGPT, Microsoft Copilot, Claude, Gemini, or similar platforms Pharmaceutical, biotech, medical device, healthcare, or life sciences experience Ability to translate AI concepts into practical business applications Excellent facilitation and presentation skills Preferred Qualifications Experience working within FDA-regulated environments Background in Quality, Regulatory Affairs, Clinical Operations, R&D, Manufacturing, or Commercial Operations Experience leading AI adoption or digital transformation initiatives To Apply Please include: A summary of your relevant pharmaceutical, biotech, healthcare, or life sciences experience. Examples of AI workshops, training sessions, or consulting engagements you have delivered. A brief outline of how you would approach this workshop. Any relevant certifications, publications, speaking engagements, or portfolio items available through your Upwork profile. Your proposed rate and any anticipated travel costs. Your availability during Q3 2026. Selection Criteria We are seeking a facilitator who can provide practical, real-world examples of AI applications in pharmaceutical or regulated environments and effectively engage business professionals with varying levels of AI experience.

Aria Technology Solutions is not a traditional B2B tech agency. We don’t build other people’s dreams or fix legacy corporate code. We are a fast-moving, asymmetric Product Factory and Venture Studio. Utilizing advanced AI agent architectures, autonomous development sandboxes (like Antigravity and Cursor), and rich datasets, we build, deploy, and operate a portfolio of programmatic micro-SaaS tools, high-yield arbitrage applications, and data-driven platforms rapidly and efficiently. Right now, our core team is lean (just the founders). We are scaling aggressively and need an AI Operations Manager to act as our technical producer, air traffic controller, and human-in-the-loop gatekeeper to keep our production conveyor belt running flawlessly. We don’t need a traditional Senior Software Engineer who wants to write hundreds of lines of boilerplate code by hand. We need a systems-oriented, tech-forward product operator. You will sit inside our AI management dashboards, directing and moderating parallel AI agent loops as they build features, handle data pipelines, and deploy code. You will be the bridge between our strategic product vision and our autonomous AI engineering engine, ensuring quality, preventing agent sprawl, and maintaining our active digital properties. Core Responsibilities AI Agent Pipeline Oversight (Air Traffic Control): Monitor parallel, multi-step autonomous agent loops across multiple workspaces. Ensure coding agents stay on track, resolve system execution blockers, and don't burn API tokens on infinite validation loops. Human-in-the-Loop Git Management: Review the AI-generated "Artifacts," preview builds, and code changes. Safely merge approved AI code into main Git branches and push updates to production via Vercel/Netlify/Google Cloud. Operational & Site Maintenance: Keep our fleet of live websites running smoothly. Monitor basic server uptimes, keep API endpoints and subscription tokens funded, and track central error logs. Property Moderation: Oversee basic user feedback loops, flag database anomalies, and keep our dynamic database updates (like SQLite/PostgreSQL automated inputs) running without data drift. What We Are Looking For Deep AI Native Literacy: You live in the modern AI tech ecosystem. You are intimately familiar with LLMs, AI coding environments (Cursor, Antigravity, Replit, GitHub Copilot Workspace), and programmatic workflows (MCP servers). Git & Stack Literacy: You must have strong Git literacy (branching, merging, PR reviews). While you don't need to be a coding wizard, you need a solid understanding of modern web stacks (e.g., Next.js, FastAPI, Python, Supabase, Tailwind) so you can spot when an AI agent is making a sloppy structural decision. Extreme Product Intuition: You can look at an AI-generated UI preview and instantly tell if it functions properly, flows logically for a human user, or if the agent cut a corner with a placeholder. The "Hacker/Founder" Mindset: You excel in high-velocity, low-friction environments. You value moving fast, testing live apps, and iterating quickly over corporate perfectionism. Why Join Aria Technology Solutions? The Future of Software: You will work on the absolute frontier of the "Vibe-Coding" economy, learning how to leverage AI to scale digital equity at a rate traditional software teams cannot match. Zero Bureaucracy: You report directly to the founders. If something works, we launch it immediately. Portfolio Variety: You won't be bored working on one legacy corporate enterprise tool for a year. You will help launch, operate, and maintain dozens of different innovative apps, keeping your days dynamic and high-impact. How to Apply To prove you are an operator who reads the details and doesn't just copy-paste an automated AI proposal, please start your cover letter with the phrase: "Ready for the conveyor belt." Briefly tell us about a time you used AI toolsets (like Cursor, custom scripts, or agents) to build or launch something quickly, and your comfort level with managing Git branches.

DESCRIPTION; I'm building a data infrastructure product for ontology-driven AI context: object types, properties, and relationships materialized ahead of query time, so AI systems retrieve connected context fast instead of rebuilding it from raw sources on every request. I need experienced eyes on the ingestion foundation before anything gets built on top of it. The deliverables are fixed (below); hours are flexible — propose what you think the work honestly takes. Rate: my budget is $50–75/hr. That's a hard ceiling — proposals above that range can't be afforded and won't be considered, regardless of quality __________________________________________________________________________ WHO SHOULD APPLY A data engineer / data infrastructure engineer who understands what an ontology and a knowledge graph are and why they matter for AI systems — connected entities and relationships as first-class context, not just tables. You don't need graph database experience; you need to get why pre-materialized, relationship-aware data beats rebuilding context from raw sources on every query. If that framing clicks for you, you're the right kind of applicant. __________________________________________________________________________ THE PRODUCT, HIGH LEVEL: The platform deploys on a client's own infrastructure — we never see their data. Clients connect their data sources, define an ontology (object types, properties, relationships), and the platform materializes it across tiered storage. Later phases add a binary serve layer, SSD/RAM caching, and GPU-parallel query execution so AI systems and data applications retrieve connected context at very low latency. Target customers: companies running AI on complex connected data (security operations, healthcare, financial services) where privacy demands private deployment and speed matters. Storage note: the current prototype uses Iceberg on GCS for development convenience, but the architecture is intentionally built for any S3-compatible storage (on-prem S3, private cloud VPC, MinIO, etc.). Portability is a design requirement, not an afterthought — the platform must never be tied to a single cloud provider. __________________________________________________________________________ WHAT EXISTS TODAY: A working Python prototype: FastAPI, PyIceberg, PyArrow, Postgres, Supabase (metadata + sync ledger), GCS as the Iceberg warehouse. Architecture and design docs are provided for orientation. The cold path is functional and tested: a 31-test production suite ran against live infrastructure at 1M–5M row scale — core correctness, concurrency, failure injection (kill mid-sync, storage outages, lease expiry), idempotency/replay, rollback, a 50-sync soak, and audit checks. All passing, with a written sign-off document you'll receive. That's exactly why I'm hiring you: tests confirm behavior I anticipated. You're here for what I didn't anticipate — structural weaknesses, hidden risks, and edge cases that a test suite written by the same mind that wrote the pipeline can't catch. I'm strong on product and systems design, not low-level data engineering. The codebase is AI-assisted, and I want a professional to find what that typically accumulates. This is a prototype built from the ground up — no live client today. The goal: ensure the ingestion foundation is genuinely solid (data coming in from source correctly, at scale, repeatedly) so a scoped MVP pilot and beta release won't break under real usage. You are validating the foundation before anything gets built on top. __________________________________________________________________________ YOUR SCOPE — THE COLD PATH, END TO END Data source → validation → identity merge → materialized ontology in Iceberg on S3-compatible storage. The data connectors are in scope — they ARE Milestone 1. The platform supports exactly three ways data comes in, and your job includes confirming each one is genuinely production-grade, not just demo-grade: Postgres — full refresh and incremental watermark sync S3-compatible object storage (CSV) — currently GCS via S3 interop, but must work against any S3-compatible store (on-prem, MinIO, private VPC) Manual CSV upload — primarily for testing/onboarding For each connector, production-grade means: real error handling (bad credentials, unreachable source, permission failures, malformed/garbage data, schema drift), clear failure messages that tell a user what broke, no silent partial ingests, and sane retry/recovery behavior. If a connector swallows errors, loses rows quietly, or fails confusingly — that's exactly the finding I'm paying for. No other connectors are planned for this milestone. Three connectors that work correctly under stress beats ten that mostly work. Focus areas across the pipeline: Connectors — production-readiness and error handling as described above Identity & matching — entities staying consistent across syncs (PK merge, fingerprint mode, composite keys) Sync semantics — full refresh vs incremental watermark sync, replay idempotency, delete behavior Relationships — FK→PK edge materialization, rebuild triggers, orphan handling, stable node identity Versioning & audit — Iceberg snapshots, rollback, schema change lineage, sync ledger completeness Reliability — failure modes, partial writes, lock/lease behavior, silent wrong-data risks Code structure — dead code, duplication, coupling, fragility; source-specific logic must stay contained in each connector and never leak into the shared pipeline Explicitly out of scope: GPU execution, query kernels, binary serve formats, caching layers, query-time serving, and any new connector types — all future phases. Your scope ends at correct, versioned, audited data in Iceberg. __________________________________________________________________________ DELIVERABLES (in priority order) Prioritized written assessment — what's pilot-ready as-is, what must be fixed before a real pilot customer (with specific recommendations), and what the existing test suite missed (edge cases, risks, gaps). Active code changes — implement fixes for the highest-priority issues you find, directly in the repo. You'll have full repo access. I'm open to architecture changes and refinements as long as they're clearly explained with reasoning. A change log that teaches — for every change: what you changed, why it mattered, what it fixes or prevents, and what to watch for going forward. This isn't paperwork — I'm making a local engineering hire for the next milestone, and your write-ups become the onboarding record. Everyone who touches this codebase after you should learn from what you found. Fixes go deepest-risk-first. What you get from me: repo access, architecture/design docs, the test suite + sign-off report, and async availability for questions. __________________________________________________________________________ ***REQUIRED EXPERIENCE: 1)Production Python data pipelines 2)Apache Iceberg, Delta Lake, or Hudi (or strong Parquet/data-lake work) 3)Postgres 4)Merge/upsert, idempotency, watermark/CDC patterns Building or hardening data connectors that real users depend on************* __________________________________________________________________________ WHERE THIS CAN GO: This starts as a fixed-scope review. Separately, I plan to make my first part-time/full-time engineering hire locally (Dallas) to build Milestone 2 and beyond — SSD caching, serve layers, containerization, and microservices as the platform scales. For the right freelancer, there's opportunity to stay engaged on recurring scoped work — reviewing the foundation as it evolves and working in conjunction with that future hire. Not required, not promised — but the door is open if the work is strong. __________________________________________________________________________ *********HOW TO APPLY — READ CAREFULLY***** Answer this one question in your proposal, briefly and in your own words: "You're building a pipeline that ingests from Postgres and S3-compatible storage and materializes a connected ontology (entities + relationships) into Iceberg. How do you design the sync process to be reliable and idempotent — especially around watermarking, commits, and failure handling between steps?" Include your proposed hour estimate for the deliverables above. Get creative — attachments and notes welcome. Note on AI-generated proposals: I use AI heavily myself — but if your proposal or screening answer is clearly AI-generated boilerplate, you will be automatically rejected without consideration. I'm hiring your judgment and experience, not your ability to paste a prompt. Short, direct, human answers. __________________________________________________________________________ A NOTE ON TECHNOLOGY BOUNDARIES: ***QUICK EXAMPLE*** FastAPI and Iceberg are what the platform uses today, not permanent decisions. As the product scales, we may want to run FastAPI alongside a second framework, replace it entirely, or eventually move away from Iceberg toward a custom storage format optimized for the GPU serve layer. Those should be engineering decisions made on merit, not decisions we're forced into because the current code makes swapping painful. What I need confirmed: is the codebase modular enough that a change like that stays contained? Core business logic (validate, merge, materialize, version) should never be tangled directly with infrastructure. API routes should be thin entry points that hand off to service logic, not where business logic lives. Iceberg writes should be isolated behind a single abstraction. If those boundaries are clean, replacing or extending a technology layer is a focused engineering effort. If they're not, it touches everything and becomes a mess under deadline pressure with a full team. Flag anywhere that boundary is broken. That's a priority finding. __________________________________________________________________________ FINAL REMARKS: NDA & IP protections This engagement requires signing an NDA and IP assignments agreement before work begins; standard protections given you'll have full repo access to a pre-launch product. Documents are provided on day one; nothing unusual in them. If that's a dealbreaker, please don't apply.

Job Description: We are looking for a skilled, "under-the-hood" Full-Stack Developer to help build out Lafayette Academy’s online portal. We have clear visual layouts, a working offline prototype, and a live front-end dashboard currently hosted on Vercel. We use AI heavily in our workflow for strategy, logic, and rapid drafting. However, we do not want an AI-only prompt engineer. We need a traditional, foundational developer who understands actual code architecture, databases, and deployment systems. If the AI generates a buggy script, you must have the depth of knowledge to debug it manually and make it work. What You Will Do: Take existing static mockups (HTML/CSS/Next.js components) and integrate them into our live Vercel environment, OR help create new mockups if the ones we have need to be upgraded. Connect user interfaces to a secure database (like Supabase or Firebase) to handle real-time student data. Help bridge our frontend to API endpoints (like OpenAI) to power our live "Personalization Cues" for instructors. Troubleshoot, debug, and optimize existing code when automated tools hit a wall. Our Tech Stack Focus: React / Next.js Vercel Hosting Tailwind CSS Database integration (SQL/Supabase/Firebase) To Apply: Please start your proposal with the words "Under the Hood." This proves you read the description. Tell us briefly about a time you had to manually fix a complex database or code glitch that automated tools couldn't solve.

We are developing a custom internal Electronic Health Record and Personal Health Record system to manage provider notes and insurance claims. We are currently utilizing Claude (AI) to build the foundation of our codebase and are hosting on Google Cloud Platform with existing Business Associate Agreements in place.  While our hosting environment is secure, we require a developer with deep expertise in healthcare security and HIPAA compliance to perform a technical audit of our code and architecture. The Challenge: Our code is AI-assisted. However, unlike standard AI-generated projects, we use a highly structured approach. We maintain a comprehensive code source readme and strict system parameters to ensure Claude produces clean, modular, and consistent code that closely mirrors human-written standards. We need an expert who can evaluate the security, logic, and efficiency of this application. We are specifically looking for a partner who can provide human-in-the-loop oversight to ensure the application itself meets all HIPAA technical safeguards. Key Responsibilities: 1. Code Review: Audit modular, AI-generated code for security vulnerabilities including injection, broken authentication, and improper data handling. 2. Security Architecture: Validate that data handling within Google Cloud Platform meets HIPAA technical safeguards. 3. Architecture Validation: Verify that our code source guidelines are technically sound and that the AI is following established security patterns. 4. Compliance Integration: Ensure the application logic supports mandatory audit logs, access controls, and encryption in transit and at rest. Required Qualifications: 1. Proven experience with HIPAA/HITECH compliance in a software development context. 2. Strong background in full-stack development. 3. Experience with Google Cloud Console and healthcare-specific cloud architecture. 4. Professional experience with insurance claims processing or clearinghouse integrations is preferred. 5. Ability to work with AI-assisted development workflows; we need someone who can refine and validate output within our existing governance framework. We are looking for a senior developer or security engineer who can help us bridge the gap between our current development and a production-ready, fully secure system. Background check and references required

## Project at a Glance - Project stage: Partially built; bootstrapped project where efficiency, speed, cost, and lean execution matter. - Expected project duration: Approximately 1 to 2 months. - Engagement type: Independent contractor / hourly engagement only. - Scale target: The app should be architected with future growth in mind, including a target capacity of 80,000+ monthly active users with reasonable headroom to scale without avoidable rework, security degradation, or performance issues. - Security posture: SOC 2 readiness should be considered from day one; certification may occur later. - Meetings: One weekly video sync of up to 60 minutes may be scheduled by mutual agreement and should be accounted for in the contractor’s proposed budget. ## Overview We are building a production-grade, multi-tenant SaaS web application designed for enterprise-level scale, security, and reliability. The application may handle employee data and is being built with SOC 2 readiness in mind from day one. This is a bootstrapped project. Speed and lean execution are critical, and every decision should balance quality with pragmatism. The product is being designed to last, scale, and withstand technical, security, and operational scrutiny. We are seeking a U.S.-based individual senior full-stack engineer who can personally lead the web app development scope through production-ready implementation, end to end. No outsourcing outside the U.S. No agencies. ## Technology Stack - Front-end: Next.js App Router, TypeScript, Tailwind CSS - Backend / API: Next.js API Routes, Supabase Edge Functions, FastAPI / Python - Database: Supabase PostgreSQL - Authentication: Supabase Auth, OAuth, SSO, MFA - Authorization: RLS / Row-Level Security, RBAC - Realtime: Supabase Realtime - LLM / AI: OpenAI / Anthropic / Gemini-compatible LLMs - Billing: Polar.sh - HRIS Integration: Unified third-party connector - Email Delivery: Resend - Analytics: PostHog - Error Monitoring: Sentry - Infrastructure: Vercel + Supabase - CI/CD: GitHub Actions - Testing: Vitest / Jest, Playwright - AI Agents: Agentic workflows, tool use, and related architecture - MCP Integrations: MCPs for ChatGPT, Claude, Gemini, or similar environments - Additional technologies may be used. ## What We Are Looking For - Experienced full-stack SaaS product engineer with a strong, verifiable portfolio - Deep expertise in Next.js and TypeScript - Production-grade Supabase experience, including RLS, Realtime, and Edge Functions - Python back-end development experience with LLM integration, including RAG pipelines, memory, or fine-tuning workflows - Experience implementing subscription lifecycle flows and seat-based access control end to end - A genuine standard for clean, well-organized, maintainable code - Demonstrated ability to design systems that can scale horizontally without structural rework - Demonstrated ability to work efficiently in a lean, bootstrapped environment - Security-first development practices, especially when handling sensitive or regulated data - Clear, prompt professional communication - Experience building AI agents or agentic workflows - Experience building MCP integrations for ChatGPT, Claude, Gemini, or similar platforms - Experience designing hierarchical multi-tenant account structures with seat-based access control ## Strongly Preferred - Hands-on experience building RAG pipelines and LLM fine-tuning workflows in production - Experience handling employee or HR data, including PII access controls, audit trails, and data residency considerations - Experience building toward SOC 2 readiness in a prior engagement - HRIS or enterprise HR system integration experience - Familiarity with OWASP, NIST CSF, or CIS Controls ## This application is being built to last and may handle sensitive employee data. We are looking for an engineer who takes code quality, data responsibility, lean execution, and long-term system health seriously. ## Please answer all 5 screening questions in your response. ## Communication - Contractor should identify normal availability windows and provide timely responses, generally within one business day during those agreed availability windows. - Day-to-day communication will generally be async through the applicable platform or contract workroom. - One weekly video sync of up to 60 minutes may be scheduled by mutual agreement for status updates, completed-work summaries, blockers, and upcoming priorities. Contractor should account for this meeting time in the proposed hourly rate or budget. - Pre-engagement sales, proposal, or introductory scoping discussions are not billable. ## Confidentiality and IP Project details are shared only after the client’s NDA is executed. If both parties decide to move forward, a separate IP Assignment Agreement is required before any offer is accepted or substantive work begins. This is an independent contractor / hourly engagement only and does not include full-time employment, salary, benefits, equity, revenue share, product ownership, or any ongoing engagement beyond the agreed scope.

Seeking an AI developer to create a conversational AI companion with a custom personality. The project involves designing a unique personality and integrating it into a chatbot. The ideal candidate will have experience in AI development and personality customization. The role requires collaboration with a writer to ensure the personality aligns with the character's traits and backstory.

We are looking for an expert backend developer and automation engineer to extend an existing, production-grade Model Context Protocol (MCP) server and overhaul its orchestration layer. The headline correction for this project: the existing Lawfather MCP is to be retained and extended, not rebuilt. It already exposes deterministic, parameterized Playwright tools for every required county portal (District Clerk, HCSO, HCDAO) and a client database. Those backend tools are the reliable layer and are not the source of the instability this project exists to fix. The instability lives entirely in the orchestration layer — the model-driven layer that decides when and how to call the tools. The fix is to move deterministic control out of model-followed prose and into code, and to host the agent on an always-on machine with persistent memory. Core Project Principles • Extend, Don't Rebuild: Retain and extend the existing MCP; do not re-implement portal scrapers from scratch. • Code Over Prompts: Deterministic logic lives strictly in tool code, never in instructions the model must remember each session. • No Caller Loops: Batch operations must run to completion server-side. No operation may require the caller (model) to loop. • Agnostic Architecture: The system must remain model-agnostic and host-agnostic. No single provider — Anthropic, OpenAI, Z.ai/GLM, or Nous — may be a hard dependency. • Privilege First: Client data stays on owned hardware; the model is never the gatekeeper of which case a file belongs to. Existing Tool Inventory (To Be Inherited As-Is) The following tools already exist on the production MCP (containerized on a local Synology NAS) and are in daily use. Re-deriving their behavior is completely out of scope: • hcdc_get_docket: Court settings by date range + bar number (District Clerk). • hcdc_check_filings: Per case: standard defense filings present vs. missing. • hcdc_download_filings: Images-tab documents: bulk OR selective by filters; dest_subfolder; dry_run. Note: The parameterized download tools already cover most retrieval requests. "All filings," "this filing," "all subpoenas," "all resets," and "everything filed that day" are argument combinations on this tool, not separate features. • hcso_locate: Defendant custody location (facility / floor / pod) by SPN. • hcdao_grab_file: Download a single named file from the DA portal Files tab. • hcdao_download_discovery: Batch / delta discovery download from the DA portal. • hcdao_download_media_alert: Batch-download files listed in a 'New Media Available' portal email. • hcdao_case_summary: Scrape the Case Jacket quick summary / DAO narrative. • hcdao_plea_offer: Scrape current plea offer + full offer history. • hcdao_assigned_ada: Assigned ADA name / email / phone on a case. • lookup_client / list_clients: Resolve / list clients from the shared client database. Scoped Work (Paid Deliverables) 1. County Case Resolver (New Tool): Find a case from partial identifiers — any subset of (name, SPN, DOB, court, cause). Searches county systems (not just the local client DB). MUST return a ranked candidate list for the user to choose from; MUST NEVER auto-select. Wrong-defendant selection is a privilege failure, not a cosmetic bug. 2. Latest-Version Retrieval: Add scope=latest to hcdao_grab_file so 'most recent' selects the newest among supplements instead of the first match. 3. Async Transcribe Tool (Skill to Tool Promotion): Build a deterministic MCP tool using Gemini 3.1 Pro Preview for transcription, followed by a second pass that sends the transcript back with case context for cleanup (speaker mapping, defense-moment preamble). Long-running: implement as an async job (submit to job id to poll to fetch), NOT a synchronous call. 4. OCR Tool (Skill to Tool Promotion): Implement a readability check on ingest. If a document is not cleanly readable, FLAG it and ASK before sending to Gemini 3.1 Pro Preview for OCR. OCR must be gated and confirmed, never automatic. 5. Server-Side Batch Jobs: Move all chunk, loop, delta, and throttle logic OFF the caller and INTO the tool code. One call runs the batch to completion. 6. Queued HCDAO Fixes: For hcdao_download_discovery, add a portal_ids filter for targeted single-file pulls and a custom output-path / Drive-folder destination feature. Known Portal Quirks to Handle from Day One • hcdc_get_docket returns a broader date range than requested; results must be filtered to the requested window. • hcdao_download_discovery delta detection is blind to files organized into dated subfolders and must be explicitly handled. • Court DG7 does not surface through standard bar-number docket lookup and requires separate handling. • The Playwright Node.js driver subprocess can die silently while database tools respond; you must health-check the driver proactively. Orchestration, Host Layer, & Deployment Topology • Target Host: Hermes Agent (Nous Research) running as the persistent shell, providing persistent memory, the scheduler, and messaging surfaces. The MCP server will plug directly into it. • Agnostic LLM Routing: Default the agent/dispatch role to the most reliable tool-calling model (currently Claude Opus). Route bulk, non-critical generations (draft summaries, transcript cleanup) to a cheaper model (e.g., GLM-5.2). No provider may be hard-wired. Per-tool pins are allowed strictly for transcription/OCR tasks (pinned to Gemini 3.1 Pro Preview). • Memory Fencing: Hermes's persistent memory and learning loops must remain enabled to accumulate facts and user preferences. However, the agent must be strictly fenced from self-editing or rewriting its own mechanical execution paths (portals, downloads, filings), which must remain frozen in MCP tool code. • Hardware Deployment Infrastructure: • Always-on Brain: M1 Pro MacBook Pro (16 GB, mains-powered, lid open) running the Hermes gateway, Messages.app, and a BlueBubbles iMessage bridge. Must be fully automated via launchd services to handle headless crash recovery, auto-login, and sleep prevention (pmset autorestart / caffeinate). • Tools and Storage: Synology NAS (10.0.0.149) hosting the Lawfather MCP container, local client folders, and Drive sync. • Private Network: Tailscale mesh across all devices for secure remote access without open inbound ports. Acceptance Criteria for Sign-Off • No batch operation requires the caller to iterate. • The case resolver returns ranked candidates and never auto-selects. • Transcription runs seamlessly as an async two-stage job surviving multi-hour files without timing out. • OCR never fires automatically on low-readability files without gated confirmation. • Zero regressions on the existing MCP tool inventory. • The Resiliency Test: The full stack successfully restarts completely unattended after a host reboot or simulated power loss, and is reachable via iMessage/SMS immediately after. • Self-editing is fenced on mechanical download/filing paths. Hard Guardrails • Privilege: Downloads route strictly to the correct client folder; a wrong-case match is treated as a severe defect, not a warning. Privileged audio/discovery data stays on owned hardware where the chosen model allows. • Determinism: Repeatable steps live entirely in tool code, never in prompts. • Agnosticism: Model and host layers must remain fully swappable without modifying the core MCP tools. Before quoting "done," you will be expected to confirm live portal behaviors regarding District Clerk document labels, DA portal stable identifiers, and county search surfaces. How to Apply Please submit a proposal detailing your specific experience with MCP architectures, Playwright browser automation, and macOS/Docker DevOps automation. Anti-Bot Filtering: To prove you read this entire scope, please start your application with the phrase "PROTECT THE LAW" in all caps. Automated or generic copy-paste applications will be instantly rejected.

About the Role I'm a full-time systems engineer and entrepreneur running multiple active businesses, a growing content brand, and personal operations simultaneously. I had a general VA before the role didn't stick because it lacked structure and real ownership. I'm not looking for a task-taker. I need a proactive operator who thinks ahead, builds systems, and executes without hand-holding. This is a high-trust, high-ownership role. If you thrive in chaos and bring order to it this is for you. Core Responsibilities 1. Notion Systems Management (MANDATORY) Managing workspace, dashboards, and project trackers Building and maintaining execution systems, SOPs, and checklists Time-blocking calendar and running weekly reviews Turning raw ideas into structured action plans Examples: CRM pipelines, content calendars, accountability systems 2. Executive Assistant / Personal Operations Calendar management · deadline tracking · travel coordination · inbox organization · vendor communication · research · follow-up management · appointment scheduling · briefing doc creation. 3. Content Operations / Social Media Support Organize content ideas · manage the content calendar · repurpose content across platforms · draft captions · research trends · coordinate posting workflows · manage brand assets. Platforms: Instagram · TikTok · X/Twitter · LinkedIn Youtube Shorts Canva, CapCut, basic video editing. 4. Media / Camera Coordination (Bonus) Experience helping coordinate shoots, creating shot lists, organizing filming schedules, or working with videographers is a big plus. If you have personal production skills, mention them. --- Required Skills - Advanced Notion (must demonstrate proficiency) - Executive assistant or operations experience - Strong written English and communication - Calendar and project management - Social media workflow understanding - Detail-oriented with strong follow-through - Problem-solving mindset Bonus: Canva · CapCut · Video editing · Content strategy · Stan · AI tools (ChatGPT, Claude, etc.) --- Ideal Candidate You are highly organized, sharp, and self-directed. You take ownership and bring order to chaos. You communicate proactively, flag issues early, and execute without being micromanaged. You've supported a busy entrepreneur or executive before — that experience is a major plus. You're available during Central Time (GMT-6) business hours. This is a long-term working partnership, not a gap fill.