AI/ML Developer – Agentic AI

Job title: AI/ML Developer Agentic AI Location: St. Louis, MO
Candidates: St. Louis
Experience: 10+ Years Job Description

We are seeking an experienced AI/ML Developer to join our Agentic AI Platform Team. The ideal candidate will have strong production-level Python development experience along with hands-on expertise building LLM-powered agents, RAG pipelines, and multi-agent orchestration systems.

The developer will work closely with the Platform Architect and engineering team to design, develop, and deploy scalable AI solutions that directly support field technicians in production environments.

Key Responsibilities

• Design, develop, and deploy LLM-powered agents using LangChain and LangGraph.
• Build and enhance multi-agent orchestration pipelines with conditional routing, state management, and error recovery.
• Develop RAG pipelines using embeddings, vector search, hybrid search, re-ranking, and Reciprocal Rank Fusion (RRF).
• Implement tool-calling agents supporting parallel API execution, sequential enrichment, and response summarization.
• Develop real-time conversational AI streaming using WebSocket and SSE.
• Integrate applications with Azure OpenAI APIs, including circuit breakers, retries, fallback chains, and resilient service patterns.
• Implement advanced prompt engineering, including system prompts, few-shot prompting, structured JSON outputs, and dynamic prompt management.
• Design and implement multi-modal AI capabilities, including image analysis using vision models.
• Develop production-quality Python applications with proper error handling, logging, observability, and unit testing.
• Work with PostgreSQL and asynchronous database technologies.
• Participate in code reviews, architecture discussions, Agile/Scrum ceremonies, and sprint delivery.
• Collaborate with architects and engineering teams to design scalable microservices and distributed systems.

Required Skills & Experience

• 10+ years of software development experience with strong hands-on Python expertise.
• 2+ years of hands-on LLM/Generative AI development experience.
• Strong experience with LangChain, LangGraph, or equivalent LLM agent frameworks.
• Hands-on experience developing RAG pipelines, including:
  • Embeddings
  • Vector search
  • Hybrid search
  • Re-ranking
  • Answer generation
• Experience with OpenAI LLM APIs, including Chat Completions, Responses API, streaming, and tool/function calling.
• Strong Async Python experience with asyncio, httpx, and FastAPI.
• Strong understanding of prompt engineering, system prompts, few-shot prompting, and structured JSON output.
• Experience implementing circuit breaker, retry, fallback, and resilient service patterns.
• Hands-on experience with PostgreSQL and asynchronous ORM technologies such as SQLAlchemy Async and Alembic.
• Experience with Git, CI/CD, Docker, and Kubernetes.
• Strong system design skills with experience in microservices, distributed systems, and API design.

Nice-to-Have Skills

• Hands-on experience with LangGraph StateGraph, including conditional edges, node pipelines, and compiled graphs.
• Experience developing multi-agent systems, orchestration/routing, and RBAC-based access control.
• Experience with Langfuse or similar LLM observability platforms, including tracing, token usage, and latency monitoring.
• Experience with WebSocket and SSE streaming.
• Experience with multimodal AI and vision models for image analysis.
• Experience with vector databases such as OpenSearch, Pinecone, or pgvector.
• Experience with AWS, including Aurora PostgreSQL, SSM, IAM, and EKS.
• Experience in Telecommunications or Field Service domains.