AI Engineer: LLM, RAG & MLOps Expert

Programmers; United States; On-site; USD 120,000 - 180,000; Full time

Job summary

Programm ers is seeking a seasoned AI/ML engineer to design and implement production-grade AI systems. You will work on Python-based services, asynchronous APIs via FastAPI, and end-to-end ML workflows, including testing, deployment, monitoring, and HITL feedback loops.

You will optimize retrieval with RAG, embeddings, and vector databases, while ensuring grounding and accurate model behavior across multi-agent orchestration and memory management in distributed environments.

Skills

Python

Async programming

API Development (FastAPI)

Testing (unit, integration)

Debugging distributed systems

LLM Fundamentals

Prompt Engineering

Tokenization

Context windows

Model selection

Handling hallucinations

RAG

Document ingestion

Chunking strategies

Embeddings

Vector database (pgvector)

Hybrid search

Re-ranking & relevance

Agentic frameworks

Multi-agent coordination

Memory management

Workflow orchestration

Evaluation & observability

LLM evaluation metrics

Prompt/version tracking

Logging & tracking

HITL feedback loops

Deployment & MLOps

Docker

CI/CD

Monitoring

Tools

Docker

pgvector

BM25

Job description

Programm ers is seeking a seasoned AI/ML engineer to design and implement production-grade AI systems. You will work on Python-based services, asynchronous APIs via FastAPI, and end-to-end ML workflows, including testing, deployment, monitoring, and HITL feedback loops.

You will optimize retrieval with RAG, embeddings, and vector databases, while ensuring grounding and accurate model behavior across multi-agent orchestration and memory management in distributed environments.