We are looking for an entry-level Software Engineer who is strong in computer science fundamentals and algorithms. You will work on real-world software problems. This role suits someone who enjoys bridging theory and practice: thinking carefully about problem formulation, writing clean and efficient code, and taking ownership of results end-to-end. ROLE OVERVIEW You will work within a small, cross-functional team to build software. You will be expected to think algorithmically, write quality code, and communicate your findings clearly to non-technical stakeholders. KEY RESPONSIBILITIES Analyse product and business requirements provided by the team. Select appropriate algorithms and architectures based on data characteristics, constraints, and performance requirements. Design and implement efficient data structures and algorithms. TOOLS & STACK Knowledge in these areas are preferred. Postgres and Mongo DB Machine learning and LLM frameworks Middleware and mobile concepts especially React-Native and Javascript/NodeJS Infrastructure: Basic familiarity with GCP or AWS Version control: Git QUALIFICATIONS Bachelor's degree in Computer Science is preferred Strong foundations in algorithms and data structures — able to reason about complexity and write efficient code. Good understanding of machine learning and LLM concepts Clear written and verbal communication; able to explain model behaviour and trade-offs to non-specialists.

EroFlow Intelligence is an enterprise-grade, autonomous AI orchestration pipeline designed to mitigate global supply chain disruptions for aerospace manufacturing. Built using a multi-agent framework, the system automates the entire lifecycle of risk detection, impact analysis, and procurement mitigation without requiring human intervention for standard operational anomalies. The architecture coordinates three specialized, asynchronous AI agents that communicate via a centralized event bus to solve complex logistical bottlenecks in real-time. Core Agent Architecture & Workflow 1. The Sentinel Agent (Data Ingestion & Extraction) Role: Continuous Global Monitoring. Function: Utilizes advanced LLM-driven web scraping and unstructured data extraction to monitor global news feeds, geopolitical shifts, weather anomalies, and shipping port telemetry. Trigger: If it detects a disruption (e.g., a port strike or critical mineral shortage), it extracts key entities (materials affected, estimated delay times) and passes a structured JSON payload to the orchestration layer. 2. The Impact Assessment Agent (Predictive Modeling) Role: Deep Cross-Referencing & Analytics. Function: Upon receiving a trigger, this agent cross-references the disrupted material with the company’s internal ERP (Enterprise Resource Planning) database and current inventory levels. Output: It runs a predictive analysis to determine exactly which production lines will stall and calculates the financial risk, assigning a high/medium/low priority score to the event. 3. The Mitigation & Logistics Agent (Autonomous Execution) Role: Operational Resolution. Function: If the risk score exceeds a specific threshold, this agent is authorized to take action. It autonomously queries pre-vetted alternative suppliers via APIs, negotiates standard volume pricing based on historical contract data, drafts a comprehensive procurement proposal, and queues the purchase order for final human sign-off (or executes it automatically if under a certain dollar cap). Technical Stack (The Blueprint) Frameworks: LangGraph / CrewAI (for multi-agent state management and deterministic routing). Core Language: Python 3.11+ Data Layer: PostgreSQL (for ERP syncing) & Pinecone / Qdrant (Vector database for storing and querying supplier contract PDFs and historical compliance documentation). LLM Orchestration: OpenAI GPT-4o / Anthropic Claude 3.5 Sonnet utilized via structured outputs (Pydantic parsing) to ensure strict API data integrity. Hosting & DevOps: Containerized via Docker, orchestrated via Kubernetes, and deployed on AWS with asynchronous task queues managed by Celery and Redis. Quantifiable Business Results (The Hook) 92% Reduction in supply chain anomaly response time (from 48 hours down to 14 minutes). Automated Recovery: Successfully mitigated over 140 potential production line stalls autonomously in simulated stress tests. Cost Efficiency: Saved an estimated $1.2M in expedited shipping fees by predicting bottlenecks 10 days before they impacted manufacturing floors.

We need a senior architect to lead the design and build of a multi-model routing control plane, then guide a small senior team through the build. The control plane sits in front of a family of AI systems and decides, for every request (text, image, video), the cheapest path that still meets quality: cache, reuse, a small or local model, an on-device model, an open-weight model, a fine-tuned model, or a higher-cost frontier fallback. It must route not just across models but across compute: CPU, GPU, on-device, and edge. The north-star metric is the share of requests served without touching an expensive frontier GPU, and the resulting cost reduction on a representative workload. The ambition is to move the majority of eligible workload off frontier GPUs onto cheaper paths without degrading output. This is not a chatbot project and it is not a thin wrapper over hosted APIs. You will own the architecture, define the routing logic, and lead execution. We need someone who thinks in systems, not individual model calls. Context (so you understand what we need delivered) The router is one component of a larger AI platform, not a standalone product. It must be model-agnostic: open-weight, fine-tuned, and proprietary models get swapped in and out behind a stable interface without rearchitecting. You will coordinate with a separate team that owns the models you route to. The initial engagement is a 60 to 90 day POC with a working demo of the router as the goal, followed by technical leadership through the build. What You Will Own - Control plane architecture: request intake and normalization, classification, routing taxonomy, model-selection rules, fallback logic, cache and reuse rules, logging and telemetry, and the evaluation feedback loop. - Model-agnostic interface: clean, stable contracts so models and execution paths swap in and out without rework, and so the separate team that owns the models can work independently of the routing layer. - Cost optimization across compute, not just models: reduce unnecessary GPU usage while preserving quality, using exact and semantic cache, existing output reuse, lightweight and small-model routing, batching, CPU offload, on-device and edge execution where appropriate, and a clear fallback hierarchy. The explicit goal is to shift a large share of workload off frontier GPUs. Generative caching and reuse: caching text is straightforward. Caching generative image and video is not, since the same prompt should produce variation rather than an identical result. We need a credible approach to reuse at the asset or component level, not just for text. - Evaluation loop: a framework that scores output quality by content domain and flags weakness, so the training team can target improvements instead of retraining broadly. Track output quality against intent, failure modes, cost per route, latency per route, cache hit rate, fallback rate, and regeneration rate. - Execution plan and technical leadership: an architecture diagram, recommended POC scope, milestones, infrastructure assumptions, and risks that leadership can review, plus hands-on architecture review and task breakdown. You will lead a small senior team (up to 4 engineers) through the POC build. Ideal Background - You have led or architected production AI infrastructure involving several of the following: multi-model orchestration and LLM routing, multimodal AI, model serving, inference cost optimization, GPU cost reduction, CPU and on-device inference, open-source and fine-tuned model deployment, evaluation pipelines, semantic caching, and AI observability. - You have deployed in at least one constrained environment: on-prem, self-hosted, air-gapped, or data-residency-restricted. You know what breaks when you cannot lean on a single cloud. - You can lead. This is a technical lead role, so you will set architecture, break down work, review the team's output, and keep the build on track. Specific tools matter less than the ability to architect the system correctly and lead execution. We are not looking for someone who only builds basic chatbot workflows, only uses hosted APIs without understanding the underlying infrastructure, or works as a prompt engineer alone. Deliverables - The initial engagement should produce a control plane architecture blueprint, a routing taxonomy, a POC execution plan with milestones and success criteria, and an evaluation and feedback framework, with a working router demo as the 60 to 90 day target, followed by technical leadership of a small team through the build. Screening Questions - Describe the most relevant AI routing, model-serving, or inference infrastructure system you have personally designed or built. What was routed, what models or execution paths were involved, and what role did you own? - How would you design a router that decides whether a request should use cache/reuse, a smaller or local model, an open-weight or fine-tuned model, or a higher-cost frontier fallback, across both CPU and GPU? - For generative image or video requests, how would you approach caching or reuse when the same prompt should still allow variation? Please be specific. - What metrics and evaluation loop would you use to prove the router is reducing cost without degrading output quality, and to help a separate model-training team identify weaknesses? To Apply Answer the questions above to the best of your ability. Summarize your most relevant routing or inference-infrastructure work, link any repos or examples, give your high-level approach to a control plane that cuts GPU usage while preserving quality, and note your availability and whether you have led a small engineering team before.

**Job Description:** Join our team to collaborate with software engineering, product, analytics, and business stakeholders in delivering high-performance data solutions for operational reporting, business intelligence, advanced analytics, and AI initiatives. **Key Responsibilities:** **Data Architecture & Platform Design** - Evolve data architecture for operational and analytical workloads. - Implement scalable data warehouses, lakes, and lakehouses. - Establish data modeling standards and best practices. - Modernize data platforms using Azure cloud technologies. **Data Engineering** - Develop and maintain scalable ETL/ELT pipelines. - Build data integration solutions using Azure services. - Ensure data quality through monitoring and automation. **Performance & Optimization** - Optimize SQL queries and data pipelines for efficiency. - Analyze large datasets to improve performance. - Collaborate with engineering teams to enhance database design. **Data Quality & Reconciliation** - Establish data validation and auditing processes. - Resolve data discrepancies across systems. - Maintain data quality standards. **Analytics Enablement** - Support data models for reporting and analytics. - Collaborate with stakeholders to translate requirements into solutions. - Enable self-service analytics through well-governed datasets. **Required Qualifications** - 7+ years in Data Engineering/Architecture. - Expertise in enterprise-scale data architectures and SQL. - Experience with ETL/ELT in cloud environments. - Strong understanding of data warehousing and governance. **Technical Skills** - Required: Azure SQL, Data Factory, Synapse Analytics, SQL Server, data modeling, and performance tuning. - Preferred: Microsoft Fabric, Azure Data Lake, Apache Spark, Python, CI/CD, and AI/ML data platforms. **Preferred Experience** - Experience with SaaS and large-scale datasets, particularly in data-intensive industries like healthcare. - Designing platforms for advanced analytics and business intelligence. **Success Metrics** - Reliable and scalable data platforms. - Trusted reporting with strong data quality. - High-performance environments that support business growth and analytics initiatives.

I'm currently using Claude, Google Workspace, App Script and Lambda on AWS to pull data out of an operation software called Fullbay to automate a bunch of different aspects of our business. I'm a former software engineer, but now own a medium sized business in Denver and I want someone to help me continue these efforts. For the most part, these efforts consist of many, but small projects that pull data out of the ops software, push it into a Sql server db, and then compare data across google chat, google email, workspace calendar, hubspot, and fullbay to find specific issues with our staff and workflows and notify and track and report. A lot of cool, quick projects that I need help with. I would strongly prefer someone that lives near commerce city colorado so that they can get to know the business.

Sphere Inc. is building a new AI-powered SaaS platform for the U.S. healthcare industry. We're looking for a senior engineer who enjoys building products from scratch, making technical decisions, and shipping production-quality software. This is an MVP that will quickly transition into production, so we're looking for someone who is comfortable owning architecture, development, deployment, and AI integration. We're developing a HIPAA-compliant Care Coordination Platform that helps physicians, nurses, and care coordinators manage chronic care patients more efficiently. A patient with diabetes and hypertension visits a primary care clinic. Instead of manually reviewing hundreds of pages of clinical notes, lab results, discharge summaries, and specialist referrals, the provider uploads the patient's records. The AI platform will: - Extract structured medical information from uploaded documents - Generate concise clinical summaries - Highlight medication conflicts and missing follow-ups - Detect abnormal lab trends - Recommend preventive care actions based on clinical guidelines - Generate visit notes and patient-friendly summaries - Allow physicians to approve, edit, or reject AI-generated recommendations - Maintain complete audit trails for HIPAA compliance The system must never expose PHI to unauthorized users and must meet healthcare security best practices. You'll work directly with our founders to design and build the MVP. Responsibilities include: - Design scalable backend architecture - Develop responsive React/Next.js frontend - Build secure REST APIs - Integrate OpenAI, Anthropic, or Azure OpenAI - Implement Retrieval-Augmented Generation (RAG) - Build document ingestion pipelines - Implement vector search - Build role-based access control - Design PostgreSQL database schema - Implement authentication and authorization - Deploy production infrastructure on AWS or Azure - Write automated tests - Optimize AI performance and costs Candidates should understand: - HIPAA Security Rule - PHI handling - Encryption at rest and in transit - Audit logging - Role-based permissions - Secure cloud architecture - Least-privilege access - Secrets management - BAA-aware cloud services Previous healthcare or medical SaaS experience is highly preferred. To Apply Please include the following in your proposal: - Links to recent AI SaaS or healthcare projects - Your GitHub profile - A brief description of your HIPAA or healthcare experience - 5–10 minute Loom video walkthrough of a HIPAA-compliant AI or SaaS project you personally built, highlighting the architecture, technical decisions, and your specific contributions.

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.

We're building an AI health companion for women's health and need an experienced AI Architect for weekly consulting sessions (3-5 hours/week). What You'll Do Meet with our team 1-2x per week to review architecture and provide technical guidance Help optimize our AWS Strands/RAG integration for latency, cost, and scalability Advise on conversation management, context handling, and orchestration decisions Guide us through key technical tradeoffs as we move from prototype to production Our Stack Django backend, Flutter frontend, AWS Strands What We Need 5+ years with AI/ML in production, especially RAG/LLM integration and orchestration Experience with AWS Strands and Bedrock Track record with conversation AI architecture and scaling constraints Bonus: healthcare/HIPAA experience, startup advising, Django/Python knowledge Details 3-5 hours/week, flexible remote schedule Initial 3-month engagement Mix of live calls and async reviews

We are a small, applied AI lab running a live, production-track AI product for an institutional financial services client. The work is technical, fast-moving, and high-stakes. We need a senior, collaborative engineer to own our data infrastructure layer. No corporate layers. Fast decisions. The Role & What You'll Own You will design, build, and maintain the hands-on engineering pipelines feeding a live AI scoring engine. In this agentic environment, data moves from 15+ heterogeneous external sources (APIs, PDFs, regulatory filings) through Bronze, Silver, and Gold layers.

Need an AWS Rekognition Custom Labels expert to improve an image classification model for identifying plumbing parts. Current model accuracy is approximately 55%. Dataset consists of approximately 300+ images per item captured with a Foldio turntable. Need assistance with: Dataset review Training strategy Classification vs object detection recommendations Improving model accuracy to 90%+ AWS Rekognition Custom Labels implementation Experience with computer vision and AWS Rekognition required. Deliverables: Review the existing dataset Create a new image capture strategy Train the model Test the model Document the entire process 2 hours of screen-sharing sessions explaining everything