AI/ML Developer

Job Title:AI/ML DeveloperLocation:St Louis (4 days onsite/week) (Candidates in STL preferred)JD:We are looking for a skilled AI/ML Developer to join our agentic platform team. You will design, develop, and deploy LLM-powered agents and pipelines that directly serve field technicians in production. You will work closely with the platform architect and contribute to the core multi-agent orchestration system.Key ResponsibilitiesDesign and develop LLM-powered agents using LangGraph and LangChain frameworksBuild and enhance multi-agent orchestration pipelines with conditional routing, state management, and error recoveryDevelop RAG pipelines with hybrid search (semantic + keyword), re-ranking, and Reciprocal Rank FusionImplement tool-calling agents with parallel API execution, sequential enrichment chains, and summarizationBuild real-time streaming capabilities (WebSocket / SSE) for conversational AI Integrate with Azure OpenAI APIs with circuit breaker patterns and fallback chainsImplement prompt engineering and dynamic prompt management (DB-backed with in-memory caching)Design and implement multi-modal AI features (image analysis with vision models)Write production-quality Python code with error handling, logging, observability, and unit testsParticipate in code reviews, architecture discussions, and sprint deliveryRequired Skills & ExperienceMust-Have10+ years of software development with strong Python expertise in production environments2+ years hands-on LLM development (LangChain, LangGraph, or equivalent frameworks)RAG pipeline experience - embeddings, vector search, re-ranking, answer generationLLM APIs - OpenAI Chat Completions, Responses API, streaming, tool callingAsync Python - asyncio, httpx, FastAPIPrompt engineering - system prompts, few-shot, structured JSON outputCircuit breaker patterns, retry logic, resilient service designPostgreSQL and async ORMs (SQLAlchemy async / Alembic)Git, CI/CD, Docker, Kubernetes basicsStrong system design skills - microservices, distributed systems, API designNice-to-HaveLangGraph StateGraph (conditional edges, node pipelines, compiled graphs)Multi-agent systems - orchestration, routing, RBAC-based access controlLangfuse or similar LLM observability (tracing, token usage, latency)WebSocket and SSE streaming protocolsMulti-modal AI (vision models, image analysis)Vector databases (OpenSearch, Pinecone, pgvector)AWS services (Aurora PostgreSQL, SSM, IAM, EKS)Telecommunications or field service domain experience#J-18808-Ljbffr