Build production-grade AI infrastructure with Python and FastAPI at EPAM Systems, supporting enterprise knowledge systems and reliable retrieval. Work across backend services and observability.

As a Python AI Engineer, you will evolve a Confluence-focused RAG chatbot into a broader agentic knowledge system. You will use Pydantic, SQLAlchemy async, asyncpg, and up-to-date retrieval pipelines. Your work will support ingestion, evaluation, agent runtime capabilities, and shared conversational platform primitives.

Key Responsibilities

Architect backend services with Python 3.11 and FastAPI

Design retrieval trade-offs involving quality, latency, cost, and safety

Build agent memory boundaries, tool sandboxing, permissions, and budget controls

Improve grounding, failure analysis, and citation enforcement





Create observability using OpenTelemetry, Prometheus/Grafana, Docker, Helm, and GitHub Actions

Requirements

Strong hands-on Python experience in infrastructure-heavy environments

Experience building CLI tools with Python, Golang, or Rust

Hands-on LangGraph, LangChain, pgvector, and retrieval pipeline experience

Experience designing LLM evaluation frameworks and regression detection

Strong Docker, Helm, GitHub Actions, and Kubernetes workflow experience

Apply Python, retrieval, agent infrastructure, and observability expertise to dependable enterprise AI systems at EPAM Systems.

📌 Python AI Infrastructure Engineer (Winnipeg)
🏢 EPAM Systems
📍 Winnipeg