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.

Summary We are deploying a 100% offline, private AI stack using LibreChat, vLLM, and RAG. The project requires setting up a local infrastructure for AI model deployment, ensuring security and privacy. The ideal candidate will have experience in MLOps and DevOps, with a focus on local AI deployments. Responsibilities include managing the deployment process, optimizing performance, and ensuring the system's reliability and security. Title: MLOps/DevOps Engineer Needed to Deploy Private, Local AI Stack (LibreChat + vLLM + RAG) Project Description: We are deploying a 100% offline, privacy-first AI portal on local hardware (Threadripper server with Dual RTX 6000 Blackwell 96GB GPUs). Must be able to work at least in a hybrid environment, preferably in-person at our NYC office. We need an expert to containerize and automate this infrastructure. The stack consists of: LibreChat frontend, MongoDB, MeiliSearch, local HuggingFace RAG, and local SLMs (Llama 3/Mistral) served via vLLM. Key Responsibilities: Configure Ubuntu server host, including NVIDIA drivers and CUDA environment. Optimize multi-GPU serving utilizing vLLM for high-throughput local inference. Build out a localized, containerized RAG pipeline with HuggingFace. Write Docker Compose and Ansible configuration scripts for automated deployment.

Looking for a principal-level engineer who lives at the intersection of GenAI and data platforms — not a prompt tinkerer, and not someone who only moves CSVs around. We’re building an applied AI product that has to stay grounded in real operational data. Think: messy multi-source events, lab/partner feeds, product telemetry, and user context — then RAG + agent workflows that don’t hallucinate policy, pricing, or clinical-ish language. The full build is a multi-quarter effort. This engagement is not that. I need the architecture done right before we hire the build team. What I need in ~10 hours A concrete, decision-grade architecture for a GenAI + data platform that we can hand to engineers and start implementing without re-litigating fundamentals every sprint. Scope (architecture / design only — no full production build) 1) Current-state teardown (1–2 hrs) I’ll share what we have today (sources, warehouses, APIs, any existing LLM experiments). I want a blunt read: what’s salvageable, what’s tech debt, where GenAI will break if we bolt it on. 2) Target architecture (majority of the hours) Design the end-to-end system across: • Ingestion + pipelines (batch + near-real-time where it matters) • Lakehouse / warehouse patterns (Iceberg or equivalent on object storage, plus analytics store) • Feature / context layer for retrieval (embeddings, chunking strategy, metadata filters, freshness SLAs) • GenAI serving path: RAG + tool-using agents, with evals and guardrails • Multi-cloud reality check — we are not religious about one vendor Tech direction I’m leaning toward (open to pushback if you’ve lived this): • AWS: Bedrock (Claude / Titan embeddings), S3, Glue/EMR or managed Spark, OpenSearch Serverless or Aurora pgvector, EventBridge/MSK as needed • GCP: Vertex AI (Gemini), BigQuery, Vertex Vector Search / AlloyDB, Pub/Sub, Cloud Run • Microsoft: Azure OpenAI, Fabric / Synapse or ADLS Gen2, Azure AI Search, Functions / Container Apps I want a primary path + a migration/hybrid story — not three half-built platforms. Prefer someone who’s actually shipped Bedrock and/or Vertex in production, not just blog-post diagrams. 3) Deliverables I will pay for • Architecture doc (decisions + rejected alternatives — why we didn’t do LangChain-everywhere, why not pure Lambda, etc.) • One clear diagram (C4 or equivalent: context + containers) • Data contracts sketch for the retrieval corpus (what lands in the index, PII handling, retention) • GenAI control plane: prompt/versioning, eval harness outline, grounding + safety guardrails • Rough cost model (steady-state monthly) and a 30/60/90 implementation sequence for a follow-on team • 45–60 min working session mid-engagement to pressure-test assumptions Out of scope for this 10-hour pass • Full pipeline implementation • Fine-tuning / training jobs • Production IaC of the whole estate • UI work Who this is for You’ve owned platforms that process serious volume, you’ve put LLMs behind real product surfaces (RAG / agents / MCP-style tool protocols), and you’ve made multi-cloud IaC choices under cost and reliability pressure. Bonus if you’ve dealt with regulated data (HIPAA/SOC2) and know where GenAI becomes a compliance problem. How we’ll work Async + one live architecture review. I’ll be decisive. If something is underspecified, call it out — don’t paper over it with “TBD microservice.” To apply Don’t send a generic AI cover letter. Tell me: 1) One GenAI system you designed (Bedrock / Vertex / Azure OpenAI — which, and why) 2) One data-platform decision you’d reverse if you could 3) How you’d spend the first 3 of these 10 hours If you’ve only done ChatGPT wrappers or only classic ETL with no retrieval layer, this isn’t the right fit — no hard feelings.

26ers is building Human + AI operating systems that help organizations improve decision quality, execution speed, and organizational leverage. We are seeking a customer-facing AI Architect who can work directly with executives, operational leaders, and technical teams to design practical AI solutions that solve real business problems. This role helps organizations identify high-value AI opportunities, redesign workflows, modernize operations, and implement Human + AI operating systems that improve execution, decision-making, and organizational effectiveness. The ideal candidate can move fluidly between customer conversations, workflow discovery, solution design, governance considerations, and implementation planning. Responsibilities • Participate in customer discovery and solution design conversations • Analyze current-state workflows and identify AI transformation opportunities • Design Human + AI operating models, agentic workflows, and operational systems that improve execution and decision-making • Create solution blueprints, implementation plans, and statements of work • Collaborate with implementation developers and technical delivery teams • Consider data governance, security, compliance, and operational requirements throughout solution design • Contribute to the development of reusable 26ers methodologies, frameworks, and institutional knowledge • Design systems that capture, structure, and operationalize organizational knowledge and institutional learning Ideal Experience • Experience designing AI-powered business workflows and operational systems • Strong understanding of OpenAI, Claude, and modern LLM-based solution design • Experience with workflow orchestration platforms, AI agents, automation systems, and API-based architectures • Strong understanding of data governance, information security, and enterprise AI deployment considerations • Experience translating business requirements into solution architectures, implementation plans, and statements of work • Customer-facing experience in consulting, solution engineering, professional services, digital transformation, or technical advisory roles • Experience conducting discovery workshops, workflow assessments, and current-state/future-state design exercises • Understanding of operating model design, workflow modernization, and organizational transformation • Strong written and verbal communication skills with executive stakeholders • Ability to leverage AI tools to rapidly produce architecture drafts, blueprints, requirements documents, implementation plans, training materials, and customer deliverables Nice to Have • Experience with Gemini, MCP, LangGraph, CrewAI, AutoGen, or similar orchestration frameworks • Experience with n8n, Make, Zapier, or workflow automation platforms • Experience with vector databases, RAG architectures, and organizational knowledge systems • Experience building or deploying multi-agent systems • Government, healthcare, financial services, or other regulated industry experience • Startup, founder, or early-stage company experience • Experience designing systems that capture institutional knowledge, operational learning, or organizational intelligence • Military, consulting, enterprise software, or transformation leadership experience Success in this role • Quickly understand a client's operating environment, workflows, and business objectives • Identify high-value opportunities for AI-enabled transformation and operational leverage • Translate customer goals into practical solution designs, implementation plans, and delivery roadmaps • Balance innovation, governance, security, and operational realities • Help organizations move from AI experimentation to operational execution This role may begin on a contract basis and expand into a longer-term strategic partnership as 26ers grows. Additional Information This is a highly collaborative, AI-first role. Successful candidates are intellectually curious, systems thinkers, and enjoy working through ambiguous business and technical problems. We value sound engineering judgment, clear communication, and thoughtful decision-making over simply producing code or documentation quickly. We recognize that AI can significantly accelerate architecture and documentation workflows. We encourage candidates to leverage AI tools appropriately as part of their work. However, we expect every deliverable to demonstrate your own judgment, critical thinking, and ability to validate AI-generated outputs. During the interview process, we may discuss your reasoning, tradeoffs, and design decisions in depth. Because we work with enterprise and regulated organizations, confidentiality, security, and professional integrity are essential. Selected candidates may be asked to execute a mutual NDA before participating in deeper architecture discussions or accessing confidential customer information. As our methodologies, systems, and intellectual property continue to evolve, all work created as part of this engagement will be considered work made for hire and assigned to 26ers AI in accordance with the engagement agreement. We are interested in building long-term relationships with exceptional people. While this engagement may begin as a contract role, outstanding contributors may have opportunities to expand into strategic, leadership, or founding-team roles as the company grows.

We're building an internal AI system that runs entirely on our own hardware (no cloud inference) against our own company data. We have a working proof-of-concept and want to get the architecture right. We need an experienced consultant to review what we've built, pressure-test our decisions, and tell us where we're wrong. This is an advisory/validation role first — we have someone doing the hands-on work; what we want is a senior second opinion to make sure we're building this the right way. What we're running today: Inference: RTX 5090 (32GB, Blackwell), Ubuntu 24.04, running llama-server (llama.cpp + CUDA) serving Gemma 4 31B-it (Q4_K_M GGUF) at a 262,144 context window. Also hosts our MCP retrieval server, PostgreSQL, and Qdrant. Embeddings: separate machine with an RTX 3060 running vLLM serving Qwen3-Embedding-4B. RAG: hybrid retrieval — Postgres full-text search + Qdrant semantic search with RRF fusion, exposed through a custom MCP server with tool-calling. Data: ingesting our own internal operational data into Postgres + Qdrant. Planned stack: LiteLLM for model routing, n8n for automation, Open WebUI for the interface, Langfuse for observability, Vault or Infisical for secrets, Keycloak/Azure AD for SSO. What we need help with: Validating our two-machine split (inference vs. embeddings) and whether our VRAM/context budget holds up under real load — specifically whether a 256K context window is real and performant on a single 32GB card or just nominal. Model selection and routing strategy: which open-weight models for which tasks, and how to structure LiteLLM routes. RAG quality: chunking, embedding dimensionality, hybrid search tuning, reranking — making retrieval actually accurate on messy real-world data. Sanity-checking our overall architecture and telling us our blind spots. You should have done: Stood up local LLM inference in production — llama.cpp/llama-server and vLLM, not just Ollama on a laptop. You understand GGUF quantization (Q4_K_M, IQ-series), KV cache, KV-cache quantization, and how context length maps to actual VRAM consumption. Real fluency in GPU sizing math — given a model, a quant, and a context window, you can tell us whether it fits on a given card and what throughput to expect. Bonus if you've worked with Blackwell / sm_120a. Built production RAG — vector DBs (Qdrant, pgvector), hybrid search, RRF fusion, embedding model selection, reranking, evaluation. Worked with agentic/tool-calling systems and ideally MCP servers. Know the open-weight model landscape (Gemma, Qwen, Llama, Mistral, Phi, Nemotron, Hermes) and their licenses well enough to advise. Production ops: systemd, Docker, model gateways (LiteLLM or similar), observability (Langfuse), secrets management, SSO.

We are seeking an AI Integration Specialist & Solution Architect to enhance our platform with advanced AI capabilities. The role involves integrating AI tools like Claude and GPT to improve user experience and automate processes. The ideal candidate will have experience in solution architecture and a strong understanding of AI technologies.

I want to build a private multi-model RAG-based Opportunity Intelligence Agent. It should support document ingestion, opportunity-specific workspaces, vector search, source citations, multi-model routing across OpenAI, Claude, Perplexity, and possibly DeepSeek, and generate strategic recommendations from both uploaded files and live web research. This is intended to become a reusable base agent capable of knowledge retrieval, web research, multi-model orchestration, document analysis, citation generation, and agent clonding and configuration. It will be used for analyzing & strategy development for project opportunities, responding to RFPs, and proposal assistance, as well as other applications.

About the Role We're looking for an experienced AI/ML developer to design, build, and deploy production-grade AI systems. You'll work on LLM-powered applications, retrieval-augmented generation (RAG) pipelines, and multi-agent architectures. This is a hands-on role for someone who has shipped real AI products—not just prototypes. Responsibilities Design and implement RAG pipelines (chunking, embeddings, vector stores, retrieval optimization) Build multi-agent systems using LangChain and LangGraph Integrate and fine-tune LLMs (OpenAI, Anthropic, open-source models) Develop and optimize prompts, tool-calling, and agent orchestration logic Deploy scalable, reliable AI services with proper monitoring and evaluation Collaborate on architecture decisions and code reviews Required Skills (Mandatory) Strong AI/ML fundamentals and hands-on experience Proven LLM application development RAG pipeline design and optimization LangChain and LangGraph (production experience) Agent / multi-agent system build experience Vector databases (Pinecone, Weaviate, Chroma, FAISS, or similar) Python (production-level) API integration (OpenAI, Anthropic, Hugging Face) Nice to Have Fine-tuning / LoRA / model optimization Cloud deployment (AWS/GCP/Azure) MLOps and evaluation frameworks (LangSmith, RAGAS) Experience with streaming, caching, and cost optimization

We're hiring a senior AI developer to build and deploy AI solutions for a fintech/credit-union platform. The work spans autonomous banking agents, fraud detection, credit scoring, and bill-pay/invoice automation — at the intersection of LLMs, cloud infrastructure, and financial-domain expertise, with security and compliance built in from the start. This is a long-term, ongoing engagement. What you'll do: AI agents & orchestration - Design, build, and deploy multi-agent systems using Amazon Bedrock Agents, LangChain, and related frameworks - Architect agentic workflows for core banking use cases: credit scoring, fraud detection, bill-pay automation, invoice management - Define agent personas, memory strategies, tool-use patterns, and escalation paths for production banking agents LLM engineering - Fine-tune, prompt-engineer, and evaluate LLMs for financial-domain tasks - Build RAG pipelines over credit-union knowledge bases, policy docs, and member data - Implement guardrails, content filtering, and compliance checks for safe, regulated outputs - Monitor performance, hallucination rates, and latency against SLAs Cloud infrastructure (AWS & Azure) - Architect and manage AI/ML workloads on AWS (Bedrock, SageMaker, Lambda, S3, IAM, VPC) and Azure (OpenAI Service, Azure ML, AKS) - Design secure, cost-optimized environments compliant with NCUA, PCI-DSS, and SOC 2 - Implement infrastructure-as-code with Terraform or AWS CDK DevOps & MLOps - Build and maintain CI/CD pipelines (GitHub Actions, Jenkins, CodePipeline, Azure DevOps) - Containerize services with Docker, orchestrate with Kubernetes (EKS/AKS) - Apply MLOps best practices: model versioning, A/B testing, canary deployments, automated rollback - Stand up observability with logging, tracing, and alerting Python development - Write clean, well-tested Python for AI pipelines, REST APIs, and data workflows - Build FastAPI/Flask microservices exposing agent capabilities to frontend and core banking systems - Integrate with financial data sources, core banking APIs, and third-party fintech services Banking applications - Build credit-scoring models using alternative data and explainable AI (XAI) - Develop real-time fraud detection with behavioral analytics, anomaly detection, and auto-decisioning - Create conversational agents for bill pay, account management, and member self-service - Automate invoice workflows: extraction, classification, approval routing, reconciliation - Partner with compliance/risk to keep AI decisions auditable, fair, and regulatory-compliant What you should have: - 5+ years software engineering; 3+ years in AI/ML or LLM engineering - 2+ years building AI for banking, credit unions, or financial services - Hands-on experience with Amazon Bedrock, LangChain, Python, AWS, and infrastructure-as-code - Working knowledge of NCUA, PCI-DSS, SOC 2, GLBA, and Fair Lending requirements - Bachelor's or Master's in Computer Science, Software Engineering, Data Science, or related field Nice to have: - AWS or Azure AI/ML certifications - Open-source LLM experience (Llama, Mistral, Phi) and self-hosted inference (vLLM, Ollama) - Vector databases (Pinecone, OpenSearch, pgvector) - Graph-based fraud networks and graph ML - AI governance / responsible AI framework experience - Prior work at a credit union, community bank, or fintech lending platform To apply, please share: - Your resume highlighting AI and banking project experience - A brief note on your most impactful AI agent or LLM project in a financial-services context - Links to GitHub, portfolio, or published papers (optional but encouraged)

Job Description: We are seeking an advanced development partner or agency to architect and deploy a secure, high-availability AI automation platform that bridges modern intelligent agents with our existing legacy infrastructure.The core of this project requires building autonomous AI agents and dynamic RAG (Retrieval-Augmented Generation) pipelines for semantic search, which must securely interface with our backend databases and legacy applications.You will lead the end-to-end development, from writing robust backend APIs and designing a responsive React JS frontend, to configuring the underlying Linux servers and automated CI/CD pipelines. Key Responsibilities: Build custom AI agents and chatbots using advanced LLM API integrations and Model Context Protocol (MCP) tooling.Develop custom web crawlers to securely ingest, index, and structure big data into high-availability databases.Modernize and migrate legacy software components (including Classic ASP, PHP, and Java) into a modern TypeScript and Node.js microservices architecture.Implement workflow automations via Zapier/Make and deeply integrate third-party systems like Salesforce, Odoo ERP, Twilio, and Stripe payments.Set up robust DevOps practices, including automated QA testing, Linux server hardening, and comprehensive monitoring/observability metrics. Required Skills & Tech Stack: AI & Automation: LLM APIs, RAG, Semantic Search, Voice/Transcription, Zapier, Make.com.Core Languages: Python, Node.js, TypeScript, PHP, Java, Classic ASP.Frontend/CMS: React JS, Modern JS Frameworks, WordPress.Data & Infrastructure: Big Data engineering, advanced web scraping, Linux/Mail server administration, VMware alternatives, CI/CD pipelines, Networking & Security.Integrations: Salesforce, Odoo, Twilio, Google Workspace APIs.Web3 (Plus): Solidity, Smart Contracts, Token operations. Project Scope & Deliverables: Size: Large-scale enterprise migration and AI upgrade.Deliverables: Fully deployed AI workflows, a modern user dashboard, migration of legacy core features, and documented DevOps infrastructure.Experience Level: Expert.Budget Strategy: Hourly or fixed-price milestone contract.