Onsite AI/ML Engineer: LLM Agents & Orchestration

Tech3pillars Technologies; St. Louis (MO); On-site; USD 140,000 - 210,000; Full time

Job summary

Tech3pillars Technologies seeks an experienced AI/ML Developer to design, develop, and deploy LLM-powered agents serving field technicians. You will collaborate with the platform architect on a core multi-agent orchestration system and build streaming, RAG pipelines, and tool-calling capabilities.

The role emphasizes production-quality Python, strong system design, and hands-on experience with LangChain/LangGraph, OpenAI APIs, and modern orchestration frameworks in a fast-paced environment.

Qualifications

• 10+ years of software development with strong Python in production.
• 2+ years hands-on LLM development with LangChain, LangGraph, or equivalents.
• RAG pipeline experience - embeddings, vector search, re-ranking, answer generation.
• LLM APIs - OpenAI Chat Completions, Responses API, streaming, tool calling.
• Async Python - asyncio, httpx, FastAPI.
• Prompt engineering - system prompts, few-shot, structured JSON output.
• Circuit breaker patterns, retry logic, resilient service design.
• PostgreSQL and async ORMs (SQLAlchemy async / Alembic).
• Git, CI/CD, Docker, Kubernetes basics.
• Strong system design skills - microservices, distributed systems, API design.

Responsibilities

• Design and develop LLM-powered agents using LangGraph and LangChain frameworks.
• Build and enhance multi-agent orchestration pipelines with conditional routing, state management, and error recovery.
• Develop RAG pipelines with hybrid search (semantic + keyword), re-ranking, and Reciprocal Rank Fusion.
• Implement tool-calling agents with parallel API execution, sequential enrichment chains, and summarization.
• Build real-time streaming capabilities (WebSocket / SSE) for conversational AI; integrate with Azure OpenAI APIs with circuit breaker patterns.
• Implement prompt management (DB-backed with in-memory caching) and dynamic prompts.
• Design and implement multi-modal AI features (image analysis with vision models).
• Write production-quality Python code with logging, observability, and unit tests.
• Participate in code reviews, architecture discussions, and sprint delivery.

Skills

Python

LLM development

Async Python

System design

LangChain/LangGraph

Prompt engineering

Distributed systems

API design

Git & CI/CD

WebSocket / streaming

Tools

LangGraph

LangChain

OpenAI API

FastAPI

SQLAlchemy async

Alembic

Docker

Kubernetes

Python async libraries

Job description

Tech3pillars Technologies seeks an experienced AI/ML Developer to design, develop, and deploy LLM-powered agents serving field technicians. You will collaborate with the platform architect on a core multi-agent orchestration system and build streaming, RAG pipelines, and tool-calling capabilities.

The role emphasizes production-quality Python, strong system design, and hands-on experience with LangChain/LangGraph, OpenAI APIs, and modern orchestration frameworks in a fast-paced environment.