Senior AI Engineer: Agentic & RAG Systems (Remote)

EPAM Systems; Georgia; On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Remote work within Georgia

Relocation opportunities

Certifications (GCP/AWS)

English language classes

Employee stock purchase plan

Bonuses for referrals

Job summary

EPAM Georgia is seeking a Senior AI Engineer to design, build, and operate production GenAI systems, focusing on reliability, latency, and cost with end-to-end ownership from architecture to on-call. The role centers on agentic workflows, RAG pipelines, and LLM-backed services with real users and real SLAs.

You will lead on Python/FastAPI services, production-grade LangChain/LangGraph, and integration with vector stores, container orchestration on Kubernetes, and CI/CD pipelines.

Qualifications

• 5+ years in software engineering with 2+ years delivering production LLM/agentic systems.
• Strong Python and FastAPI skills (async, REST, SSE).
• Experience with LangChain and LangGraph in production.
• Knowledge of vector databases (Pinecone/Weaviate/OpenSearch).
• Familiarity with cloud providers (AWS) and Kubernetes in production.
• CI/CD for AI systems (GitHub Actions/Jenkins).
• Excellent verbal/written English (B2 level).

Responsibilities

• Design agent orchestration and memory management in LangGraph/LangChain.
• Build production RAG pipelines with embeddings, chunking, retrieval, and caching.
• Own Python/FastAPI services including async handling and streaming.
• Instrument with tracing and evaluation harnesses for cost and accuracy.
• Ship via Docker + Kubernetes with CI/CD and canary gates.
• Drive model routing, prompt optimization, and cost accounting.
• Ensure GenAI safety, prompt-injection defense, and PII handling.

Skills

Python

FastAPI

production LLM

LangChain/LangGraph

Kubernetes

Docker

AWS

observability

Tools

LangChain

LangGraph

Pinecone/OpenSearch/Weaviate

MLflow/OpenTelemetry

Job description

EPAM Georgia is seeking a Senior AI Engineer to design, build, and operate production GenAI systems, focusing on reliability, latency, and cost with end-to-end ownership from architecture to on-call. The role centers on agentic workflows, RAG pipelines, and LLM-backed services with real users and real SLAs.

You will lead on Python/FastAPI services, production-grade LangChain/LangGraph, and integration with vector stores, container orchestration on Kubernetes, and CI/CD pipelines.