Backend Engineer – Core AI Infrastructure

About the role

Join Sarvam’s fast‑moving AI team to design and implement the core infrastructure that powers the company’s sovereign AI platform. You will work on highly secure, air‑gapped and enterprise‑grade environments, delivering production‑ready systems that run at scale.

Key responsibilities

• Design and build backend systems for Sarvam's atoms, including MCP servers, document ingestion pipelines, agentic frameworks, NL‑to‑action APIs, and on‑prem deployment tooling.
• Develop robust API layers that connect the AI stack to client‑side front‑ends and operational systems.
• Implement data ingestion pipelines for unstructured data such as PDFs, audio transcripts, imagery metadata, and geospatial feeds.
• Create containerised, minimal‑dependency services that can be operated in air‑gapped or highly constrained environments.
• Write clean, well‑tested, documented code and support deployment engineers with debugging and operational tooling.

Required profile

• 3–6 years of backend engineering experience delivering production systems in continuous operation.
• Strong system‑design knowledge of distributed systems, job queues, async processing, caching and failure handling.
• Proficiency in designing secure, scalable APIs (RESTful, GraphQL or gRPC) and deploying containerised workloads (Docker, Kubernetes or K3s).
• Experience with PostgreSQL, Redis and vector databases such as Qdrant, Chroma or Weaviate.

Required skills

• Python (FastAPI, asyncio, Pydantic)
• Go or Rust (optional but valued)
• Containerisation tools: Docker, Kubernetes, K3s
• API technologies: REST, GraphQL, gRPC
• Databases: PostgreSQL, Redis, vector stores (Qdrant, Chroma, Weaviate)
• LLM integration frameworks: LangChain, LlamaIndex, direct API usage