Lead Python Developer, Backend

We are seeking a Lead Python Backend Developer to deliver secure, scalable AI-driven API services and agentic workflows for LLM integration. You will own API contracts, RAG orchestration, and service reliability across distributed systems, partnering with adjacent teams to keep quality high.

Responsibilities Design and deliver backend API services plus LLM orchestration layers

Implement and operate end-to-end RAG pipelines, covering document ingestion, chunking, embedding, and retrieval optimization

Develop and wire up agent tools using orchestration frameworks

Ensure security, privacy, enterprise-grade observability, and test coverage across all backend workflows

Drive architecture choices and help shape engineering standards within the pod Collaborate with frontend engineers, data engineers, and infrastructure teams to ship cohesive solutions

Own API contracts and end-to-end service reliability, ensuring AI edge cases fail gracefully

Integrate LLMs with rigorous systems engineering, including evaluation, observability, fallback handling, and cost awareness

Build dependable, reusable orchestration frameworks and logic for downstream developer consumption

Requirements

Proven backend engineering background with 5+ years of experience in microservices and distributed systems

High proficiency in Python for performant backend services and cloud-native APIsHands-on familiarity with AWS, Docker, and ECS/EKSSolid understanding of RESTful APIs and API design principles

Strong foundation in secure coding practices with clear auth/authz fundamentals

English proficiency at B2 (Upper-Intermediate) level or higher

Nice to have Production experience with AI SDKs such as OpenAI, Anthropic/Claude, AWS Bedrock, or equivalent

Practical exposure to vector databases (Amazon Kendra, Open Search), embedding strategies, and retrieval systems

Hands-on work with Lang Chain, Llama Index, or Lang Graph Familiarity  with AI evaluation tooling or real-time APM such as Lang Smith, Langfuse, or Arize Skills in React and Type Script Experience  deploying to EKS environments at scale

Understanding of agent interoperability patterns (MCP)
Knowledge of identity and security domains (IAM, CIAM)
Familiarity with secondary languages such as Java, Node.js, or GoWe offer

International projects with top brands

Work with global teams of highly skilled, diverse peers

Healthcare benefits

Employee financial programs

Paid time off and sick leave

Upskilling, reskilling and certification courses

Unlimited access to the Linked In Learning library and 22,000+ courses

Global career opportunities

Volunteer and community involvement opportunitiesEPAM Employee Groups Award-winning culture recognized by Glassdoor, Newsweek and Linked In