Senior AI/ML Platform Engineer (LLM Pipelines)

Tech3pillars Technologies; Alaska; On-site; USD 140,000 - 210,000; Full time

Job summary

Tech3pillars Technologies is seeking an AI/ML Developer to design, develop, and deploy LLM-powered agents and pipelines serving field technicians in production. You will work with the platform architect on the core multi-agent orchestration system.

The role emphasizes building real-time streaming, RAG pipelines, tool-calling agents, and robust, production-grade Python with strong system design skills. This onsite position in St. Louis, MO involves sprint-driven development and code reviews.

Qualifications

• 10+ years of software development in production environments.
• 2+ years hands-on LLM development with LangChain/LangGraph or equivalent.
• Experience with RAG pipelines, embeddings, vector search, re-ranking.
• LLM APIs: OpenAI Chat Completions, Responses API, streaming, tool calling.
• Expertise in Async Python (asyncio, httpx, FastAPI).
• Strong prompt engineering: system prompts, few-shot, structured JSON output.
• Knowledge of circuit breaker patterns and resilient service design.
• Experience with PostgreSQL and async ORMs (SQLAlchemy async).
• Familiarity with Git, CI/CD, Docker, Kubernetes basics.
• Strong system design skills for microservices and distributed APIs.

Responsibilities

• Design and develop LLM-powered agents using LangGraph and LangChain.
• Build multi-agent orchestration pipelines with routing, state management, and error handling.
• Develop RAG pipelines with hybrid search, re-ranking, and RR fusion.
• Implement tool-calling agents with parallel API execution and enrichment chains.
• Add real-time streaming capabilities (WebSocket/SSE) for conversational AI.
• Integrate with Azure OpenAI APIs including circuit breakers and fallbacks.
• Implement prompt management with DB-backed and in-memory caching.
• Develop multi-modal AI features including vision models.
• Write production-quality Python with logging, observability, and tests.
• Participate in code reviews, architecture discussions, and sprints.

Skills

Python

LLM development

Async programming

System design

API design

resiliency patterns

Tools

LangGraph

LangChain

OpenAI API

SQLAlchemy async

Alembic

Docker

Kubernetes

FastAPI

httpx

Job description

Tech3pillars Technologies is seeking an AI/ML Developer to design, develop, and deploy LLM-powered agents and pipelines serving field technicians in production. You will work with the platform architect on the core multi-agent orchestration system.

The role emphasizes building real-time streaming, RAG pipelines, tool-calling agents, and robust, production-grade Python with strong system design skills. This onsite position in St. Louis, MO involves sprint-driven development and code reviews.