Sarvam is building the bedrock of Sovereign AI for India. The company is developing India's full-stack sovereign AI platform, building across research, models, infrastructure and applications with a singular focus on making AI genuinely work for India. Sarvam works with leading enterprises and public institutions and is backed by Lightspeed, Peak XV, and Khosla Ventures. Sarvam partners with India's leading brands, including Tata Capital, SBI Life, CRED, IDFC, and LIC.
About the RoleWe are looking for a Senior Software Engineer with 3–5 years of experience to join our team building an enterprise-grade AI orchestration platform. You will work on our agentic execution layer that integrates large language models (LLMs), third-party tools, and task graph execution to enable complex AI-driven workflows.
What You'll DoDesign and implement distributed microservices for AI agent orchestration
Build and optimise task graph execution engines for LLM-powered workflows
Develop integrations with multiple LLM providers and tool ecosystems
Create and maintain gRPC/REST APIs for real-time AI interactions
Implement document processing pipelines — ingestion, chunking, and vector embeddings
Build and maintain knowledge base systems with vector search capabilities
Build code interpreter sandboxes for safe AI code execution
Contribute to MCP (Model Context Protocol) server implementations
3+ years of production Python experience — async programming (asyncio), type hints, Pydantic
Backend proficiency: FastAPI or similar frameworks, gRPC & Protobuf, microservices patterns
Database experience: PostgreSQL (SQLAlchemy, migrations), Redis (caching, pub/sub, distributed locks)
Hands-on LLM API integration (OpenAI, Google AI, Anthropic) and working knowledge of embeddings and RAG
Infrastructure experience: Docker, Kubernetes basics, observability (logging, tracing)
Cloud experience with GCP, AWS, or Azure
Experience with vector databases such as Milvus or Pinecone
Familiarity with workflow orchestration tools like Temporal or Celery
Document processing experience — PDF parsing, OCR
Experience with the Bazel build system
Knowledge of MCP (Model Context Protocol)
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.
Skills Required
- 3+ years production Python experience (asyncio, type hints, Pydantic)
- Backend frameworks such as FastAPI or similar
- gRPC and Protobuf experience
- Microservices design and patterns
- PostgreSQL experience (SQLAlchemy, migrations)
- Redis (caching, pub/sub, distributed locks)
- Hands-on LLM API integrations (OpenAI, Google AI, Anthropic) and knowledge of embeddings and RAG
- Container and infra tools: Docker and Kubernetes basics
- Observability skills (logging, tracing)
- Cloud experience (GCP, AWS, or Azure)
- Experience with vector databases such as Milvus or Pinecone
- Familiarity with workflow orchestration (Temporal or Celery)
- Document processing (PDF parsing, OCR)
- Experience with the Bazel build system
- Knowledge of MCP (Model Context Protocol)
What We Do
We are an AI/ML research and development company on a mission to build reliable, performant, enterprise-grade AI systems at scale for India. We are committed to build the full-stack for generative AI for the rich & diverse landscape of India, mainly investing in: 1) Models: developing both efficient large scale Indic language models as well as bespoke enterprise models 2) Platform: building an enterprise-grade platform that empowers organisations to develop and ship creative and performant genAI applications at scale 3) Ecosystem: contributing to open-source models and datasets, as well as leading efforts for large scale data curation in public-good space
