Lead Backend Developer, AI Pods

We are looking for a Lead Backend Developer to deliver secure, scalable AI-driven API services and agentic workflows for our AI Pods. You will connect language models to internal systems, vector databases, and external tools via orchestration frameworks, treating LLMs as distributed components.
Responsibilities
Design and build backend API services along with LLM orchestration layers
Own API contracts and service reliability end-to-end, ensuring AI edge cases fail gracefully
Integrate LLMs with disciplined systems engineering, including evaluation, observability, fallback handling, and cost awareness
Implement and maintain advanced RAG pipelines, covering document ingestion, chunking, embedding, and retrieval optimization
Develop and connect agent tools using LangChain, LangGraph, and potentially MCP (Model Context Protocol)
Build dependable, reusable orchestration frameworks and logic for downstream developer consumption
Ensure security, privacy, enterprise-grade observability, and test coverage across all backend workflows
Contribute to architecture decisions and engineering standards within the pod
Collaborate with frontend engineers, data engineers, and infrastructure teams
Requirements
Proven backend engineering experience (5+ years) centered on microservices and distributed systems
Hands-on proficiency in Python to build high-performance backend services and cloud-native APIs
Working knowledge of AWS plus containerization with Docker and orchestration via ECS/EKS
Strong understanding of RESTful APIs and practical API design experience
Solid grasp of secure coding practices, including strong auth/authz fundamentals
English proficiency at B2 (Upper-Intermediate) level or higher
Nice to have
2+ years of hands-on experience with AI SDKs (OpenAI, Anthropic/Claude, AWS Bedrock, or equivalent) in production
Practical experience with vector databases (Amazon Kendra, OpenSearch), embedding strategies, and retrieval systems
Hands-on experience with LangChain, LlamaIndex, or LangGraph
Familiarity with AI evaluation tooling or real-time APM (LangSmith, Langfuse, Arize)
Skills in React and TypeScript
Experience deploying to EKS environments at scale
Understanding of agent interoperability patterns (MCP)
Knowledge of identity/security domain (IAM, CIAM)
Flexibility to use secondary languages such as Java, Node.js, or Go
We 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 LinkedIn Learning library and 22,000+ courses
Global career opportunities
Volunteer and community involvement opportunities
EPAM Employee Groups
Award-winning culture recognized by Glassdoor, Newsweek and LinkedIn
EPAM is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, sexual orientation, gender identity or expression, disability, protected veteran status, or any other characteristic protected by applicable law.

Work arrangement
Yes