Backend Engineer, Chanakya
Bengaluru • FullTime
Posted 5mo ago
About the job
Sarvam is building India's full-stack sovereign AI platform, focusing on research, models, infrastructure, and applications to make AI work for India. As a Backend Engineer, you will design and implement the core system infrastructure powering Sarvam's 'atoms', including MCP servers, on-prem deployment tooling, document ingestion pipelines, agentic backends, and API layers. These systems operate in constrained environments, and the architecture decisions you make will have a lasting impact. You will ship real systems and be accountable for their performance in the field.
Responsibilities
- Design and build backend systems for MCP servers, document ingestion pipelines, agentic frameworks, NL-to-action APIs, and on-prem deployment tooling.
- Build robust API layers connecting Sarvam's AI stack to client-side frontends and operational systems.
- Implement data ingestion and processing pipelines for unstructured data like PDFs, audio transcripts, imagery metadata, and geospatial feeds.
- Develop containerized, minimal-dependency, auditable systems for constrained deployment environments.
- Write clean, well-tested, and documented code.
- Collaborate with frontend engineers, data scientists, and MLOps to ship complete 'atoms'.
- Support Strategic Deployment Engineers with debugging, operational tooling, and troubleshooting.
Requirements
- 3-6 years of backend engineering experience with production systems in continuous operation.
- Strong proficiency in Python (FastAPI, asyncio, Pydantic) for production-grade systems.
- Proficiency in system design, including distributed systems, job queues, async processing, caching, and failure handling.
- Experience with API design (RESTful, GraphQL, gRPC).
- Experience with containerization technologies like Docker and Kubernetes or K3s, particularly in minimal-dependency environments.
- Database experience with PostgreSQL, Redis, and vector databases (e.g., Qdrant, Chroma, Weaviate).
- Experience integrating with LLM APIs and building agentic pipelines using frameworks like LangChain, LlamaIndex, or direct API integration.