Backend Engineers on this team are builders, not maintainers. You will design and implement the core system infrastructure that powers Sarvam's 'atoms': MCP servers, on-prem deployment tooling, document ingestion pipelines, agentic backends, and API layers. These systems run in classified, air-gapped, and operationally constrained environments -- or in enterprise environments with their own security, compliance, and integration constraints.
The architecture decisions you make will be inherited by every deployment that follows. You will ship real systems, not prototypes -- and you will be accountable for how they behave in the field.
What You'll Do
Design and build backend systems for Sarvam's atoms: MCP servers, document ingestion pipelines, agentic frameworks, NL-to-action APIs, and on-prem deployment tooling
Build robust, well-designed API layers that connect Sarvam's AI stack to client-side frontends and operational systems
Implement data ingestion and processing pipelines for unstructured data: PDFs, audio transcripts, imagery metadata, and geospatial feeds
Build for constrained deployment environments: containerised, minimal-dependency, auditable -- systems that a deployment engineer can operate without you in the room
Write clean, well-tested, documented code that other engineers can extend and deployment teams can operate
Collaborate with frontend engineers, the data scientist, and MLOps to ship complete atoms end-to-end
Support Strategic Deployment Engineers with debugging, operational tooling, and field-level troubleshooting
What We're Looking For
3-6 years in backend engineering with production systems in continuous operation
Strong Python: FastAPI, asyncio, Pydantic -- production-grade; Go or Rust is a strong plus
System design proficiency: distributed systems, job queues, async processing, caching, and failure handling
API design: RESTful and/or GraphQL; gRPC experience is a plus
Containerisation: Docker, Kubernetes or K3s; experience deploying in minimal-dependency environments
Database experience: PostgreSQL, Redis, and vector databases (Qdrant, Chroma, Weaviate, or equivalent)
Experience integrating with LLM APIs and building agentic pipelines -- LangChain, LlamaIndex, or direct API integration
Bonus Points
MCP protocol familiarity
Security-hardened API design and on-prem deployment experience
Comfort with air-gapped network constraints
Experience with enterprise security and compliance requirements (SOC2, ISO 27001, or equivalent)
Note: We are looking for people who can own the outcomes described here, not people who
match every line of this specification. If this problem excites you and you believe you can do this work, we want to hear from you.
Why Sarvam?
Sarvam is a fast-moving, high talent-density team building full-stack AI for India, working on problems that push the frontiers of AI with real population-scale impact.
Work alongside researchers, engineers, builders, and business leaders who move fast and hold each other to a very high bar
High ownership and high impact, from day one
Everything we do is AI-first, from the way we build and ship to the way we think about problems
You can work on problems that could change how an entire country learns, works, and communicates
If you want to work on problems at the frontier of AI in India, Sarvam is the place to be.