We are building secure, scalable AI-driven API services in our AI Pods team, using LLM orchestration to connect language models with internal systems and tools. As a Lead Backend Developer, you will own API contracts and reliability while engineering evaluation, observability, fallbacks, and cost-aware patterns for distributed services. Join us and apply now.
Responsibilities
-
Design and implement backend API services paired with LLM orchestration layers
-
Build and maintain advanced RAG pipelines including document ingestion, chunking, embedding, and retrieval tuning
-
Develop and integrate agent tools with LangChain, LangGraph and potentially MCP (Model Context Protocol)
-
Enforce security, privacy, enterprise-grade observability, and test coverage across backend workflows
-
Lead architecture decisions and uphold engineering standards within the pod
-
Collaborate with frontend engineers, data engineers and infrastructure teams to deliver end-to-end capabilities
-
Own API contracts and service reliability, ensuring graceful handling of AI edge cases and failures
-
Provide stable, reusable orchestration frameworks and logic intended for downstream developer use
Requirements
-
Proven backend engineering experience (5+ years) focused on microservices and distributed systems
-
Hands-on Python experience (3+ years) building high-performance backend services and cloud-native APIs
-
Expert-level knowledge of AWS, Docker and ECS/EKS in production environments
-
Solid experience designing and delivering RESTful API services
-
Strong understanding of secure coding practices with dependable auth/authz fundamentals
-
Upper-Intermediate English proficiency (B2)
Nice to have
-
2+ years of production experience with AI SDKs such as OpenAI, Anthropic/Claude or AWS Bedrock
-
Exposure to vector stores (Amazon Kendra, OpenSearch) plus embedding strategies and retrieval systems
-
Practical experience delivering solutions with agentic frameworks like LlamaIndex
-
Hands-on use of AI evaluation tooling or real-time APM platforms such as LangSmith, Langfuse, Arize
-
2+ years building React and TypeScript features alongside large-scale EKS deployments
-
Familiarity with agent interoperability patterns (MCP), identity/security domains (IAM, CIAM) and additional languages such as Java, Node.js or Go