Python AI Infra Engineer — Scalable, Production-Grade

EPAM Systems Inc; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

EPAM Systems Inc is seeking a Python AI Engineer to evolve an enterprise knowledge base platform from Confluence-focused RAG to a broader knowledge system. You will build robust backend services, design retrieval and agent runtimes, and improve grounding and observability across the stack.

You will work on hybrid retrieval, multi-source ingestion, and production-grade AI infrastructure with a strong focus on reliability and scalable architectures.

Qualifications

• Proven hands-on Python experience in platform or infrastructure-heavy environments.
• Experience building CLI tools using Python, Golang, or Rust.
• Hands-on experience with LangGraph, LangChain, pgvector, and modern retrieval pipelines.
• Experience designing evaluation frameworks for LLM-backed systems and quality measurement.
• Strong experience with Docker, Helm, GitHub Actions, and Kubernetes-centric workflows.
• Familiarity with embedding pipelines, vector search, and LLM-backed systems.

Responsibilities

• Architect and implement robust backend services using Python 3.11, FastAPI, Pydantic, SQLAlchemy async, and asyncpg.
• Design trade-offs around retrieval quality, latency, cost, safety, and operational simplicity.
• Build production-grade agent runtime capabilities including memory boundaries and tool sandboxing.
• Improve grounding, failure analysis, and citation enforcement for dependability.
• Create observability and feedback loops using OpenTelemetry, Prometheus/Grafana, Docker/Helm, GitHub Actions.
• Oversee ingestion across current and future content sources and ensure end-to-end observability.

Skills

Python programming

CLI tool development

Retrieval pipeline design

LLM-backed systems

Observability & metrics

System reliability

Tools

Docker

Kubernetes

GitHub Actions

Helm

LangChain

LangGraph

pgvector

OpenTelemetry

Prometheus

Job description

EPAM Systems Inc is seeking a Python AI Engineer to evolve an enterprise knowledge base platform from Confluence-focused RAG to a broader knowledge system. You will build robust backend services, design retrieval and agent runtimes, and improve grounding and observability across the stack.

You will work on hybrid retrieval, multi-source ingestion, and production-grade AI infrastructure with a strong focus on reliability and scalable architectures.