About Sarvam
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 Role
We are looking for high-agency engineers who can architect and build production-grade solutions using generative AI and agentic systems. As an FDSE at Sarvam, you will work directly with customers and product teams, understand their problems deeply, and ship real solutions fast -- not prototypes or demos, but things that run in production.
This is not a single opening. We have multiple positions across Samvaad, API Dashboard, Content Studio, and ARYA -- and we will match you to the team where your skills and interests fit best.
What You'll Do
The specifics depend on which product team you join. Here is what ownership looks like across each:
Samvaad
Build, deploy, monitor, and evaluate conversational AI agents across channels -- Voice, WhatsApp, website (voice and chat), and in-app -- integrating them deeply into client systems and workflows
Scope and design end-to-end technical solutions for client requirements, translating business needs into clean, production-ready architectures
Own client engagements from kickoff to go-live: manage technical communication, build strong client relationships, and keep delivery on track
Instrument and improve deployed agents: debug failure modes, tune prompts, and iterate on agent behaviour based on real usage data
Work closely with product and research to bring new model capabilities into customer-facing features quickly
API Dashboard
Build plugins, integrations, and developer-facing tooling that make Sarvam APIs easy to use and powerful to build on
Contribute to open-source projects -- writing plugins and extensions that add native support for Sarvam models across the developer ecosystem
Own the developer experience end-to-end -- from API design to documentation to onboarding flows
Build and maintain applications that showcase Sarvam's APIs in real-world use cases
Content Studio
Own end-to-end deployment of Sarvam's dubbing and live translation APIs into client and partner production environments -- from scoping and integration to go-live and ongoing support
Serve as the primary technical point of contact with clients: navigate integration requirements, debug live issues, unblock partners, and communicate clearly with both technical and non-technical stakeholders
Prototype quickly for ambiguous or novel client requirements; build managed service delivery pipelines where standard integrations don't fit, across dubbing and document translation
Contribute to platform engineering (frontend, backend, ML pipelines) during non-deployment cycles
ARYA
Build MCP (Model Context Protocol) servers and agentic backend infrastructure that power Sarvam's AI agents
Apply strong system design thinking to architect multi-agent systems: tool calling, memory, orchestration, and inter-agent coordination
Design and maintain data pipelines using messaging systems like Kafka, SQS, or RabbitMQ -- handling high-throughput, reliable event-driven workflows
Work with SQL and NoSQL databases at scale -- schema design, query optimisation, and data modelling for agentic workloads
Work with agentic frameworks like LangGraph and Google ADK, and know when to go beyond them and build from scratch
Contribute to internal tooling and infrastructure used across all FDSE teams
What We're Looking For
2-5 years of software engineering experience with a track record of building and shipping production systems
Strong Python fluency and comfort across the stack
Deep understanding of how LLMs and agents work -- context windows, tokens, embeddings, RAG, tool calling, prompt design, and failure modes; hands-on experience with both open and closed-source LLMs
Experience designing and implementing multi-agent architectures, including memory management and orchestration
Ability to set up eval pipelines and define meaningful quality metrics for agentic AI systems
Systems thinking: ability to reason about architecture, reliability, scale, trade-offs, and failure modes
High agency -- you unblock yourself, figure things out, and ship without hand-holding
Bonus Points
End-to-end deployment of working AI agents in production -- not a demo, something that does a real job
Side projects, open-source contributions, or products shipped outside of work
Prior experience in a customer-facing or product-embedded engineering role
Deep familiarity with LLM orchestration frameworks (LangChain, LlamaIndex, CrewAI, LangGraph) -- ideally able to author agents from scratch without depending on them
Experience with voice/speech models (TTS, STT, ASR), cloud platforms, or real-time media and streaming pipelines
Familiarity with Sarvam models and APIs from personal or project use
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.
Interested in this role?
We're always looking for curious minds who care deeply about building technology that matters.
Apply now