Lead Backend Developer

About the Position

We are building a Lead Backend Developer role on our AI Pods team to ship secure, scalable AI-driven API services and agentic workflows. You will orchestrate LLM interactions with internal systems, vector databases, and external tools, owning API contracts and service reliability. Apply now to help set engineering standards for dependable LLM-powered backends.

Responsibilities

• Design and implement backend API services together with LLM orchestration layers
• Develop and maintain advanced RAG pipelines across document ingestion, chunking, embedding, and retrieval optimization
• Create and integrate agent tools using LangChain, LangGraph, and potentially MCP (Model Context Protocol)
• Ensure security, privacy, enterprise-grade observability, and strong test coverage across all backend workflows
• Drive architecture choices and define engineering standards within the pod
• Collaborate with frontend engineers, data engineers, and infrastructure teams
• Own API contracts and service reliability, ensuring graceful failure handling for AI edge cases
• Deliver reliable, reusable orchestration frameworks and logic for downstream developer consumption

Requirements

• Proven track record with 5+ years in backend engineering focused on microservices and distributed systems
• Hands-on experience with 2+ years of Python used to build high-performance backend services and cloud-native APIs
• Deep expertise with AWS plus containerization using Docker and orchestration via ECS/EKS
• Solid background in designing and delivering RESTful API services
• Strong knowledge of secure coding practices, including auth/authz fundamentals

Nice to Have

• 2+ years of hands-on production use of AI SDKs such as OpenAI, Anthropic/Claude, or AWS Bedrock
• Familiarity with vector stores like Amazon Kendra and OpenSearch, including embedding strategies and retrieval systems
• Direct experience with agentic frameworks such as LlamaIndex
• Experience with AI evaluation tooling or real-time APM platforms including LangSmith, Langfuse, or Arize
• 2+ years working with React and TypeScript, plus exposure to large-scale EKS deployments
• Understanding of agent interoperability patterns (MCP), identity/security domains (IAM, CIAM), and additional languages such as Java, Node.js, or Go

We Offer

• Opportunity to work remotely from Argentina and other locations
• Be part of a dynamic team focused on AI-driven solutions
• Competitive contractor terms

About the Company

EPAM Systems is a global software engineering and product development company, delivering digital transformation and technology innovation across various industries.