Senior AI/ML Engineer - LLM & RAG Systems Lead (Onsite)

Openkyber, LLC; Atlanta (GA); On-site; USD 150,000 - 210,000; Full time

Job summary

Openkyber, LLC is hiring a Senior AI/ML Engineer to build AI agents and production-grade RAG solutions. The role emphasizes hands-on Python, LLM experience, and practical deployment skills in a fast-moving environment.

The position involves working with LangChain/LangGraph, OpenAI APIs, and distributed systems, delivering reliable, observable services. Onsite in St. Louis, MO with a focus on production readiness and performance.

Qualifications

• 10+ years of software development experience with strong Python.
• 2+ years of hands-on LLM/Generative AI development.
• Experience with building RAG pipelines and vector search.
• Experience with OpenAI/Azure OpenAI APIs and tool calling.
• Strong async Python experience with asyncio, FastAPI, and httpx.
• Good understanding of prompt engineering and structured JSON responses.
• Experience with PostgreSQL, SQLAlchemy, and Alembic.
• Experience with REST APIs, microservices, and distributed systems.
• Knowledge of Git, CI/CD, Docker, and Kubernetes.
• Experience building reliable applications with retry, error handling, logging, and monitoring.

Responsibilities

• Build AI agents and RAG solutions for production applications.
• Develop scalable ML-powered features using LangChain/LangGraph.
• Collaborate on API services built with FastAPI and async Python.
• Design robust data pipelines with embeddings, vector search, and re-ranking.
• Implement monitoring, logging, and observability for AI services.

Skills

Python

LLM development

LangChain/LangGraph

RAG pipelines

OpenAI/Azure OpenAI APIs

Async Python (asyncio)

Prompt engineering

PostgreSQL/SQLAlchemy/Alembic

REST/microservices

Git/CI/CD/Docker/Kubernetes

Logging/Monitoring

Tools

LangChain

LangGraph

OpenAI APIs

PostgreSQL

SQLAlchemy

Alembic

FastAPI

httpx

Docker

Kubernetes

Job description

Openkyber, LLC is hiring a Senior AI/ML Engineer to build AI agents and production-grade RAG solutions. The role emphasizes hands-on Python, LLM experience, and practical deployment skills in a fast-moving environment.

The position involves working with LangChain/LangGraph, OpenAI APIs, and distributed systems, delivering reliable, observable services. Onsite in St. Louis, MO with a focus on production readiness and performance.