SDE2 - API Platform
Sarvam · Bengaluru
Frontier labonsitemid-level
At a glance
Highlights
- Own core LLM API platform routing every request across model deployments.
- Build streaming infrastructure handling long-lived connections at scale.
- Engineer metering and billing to same bar as model APIs themselves.
Ideal candidate
Backend engineer who owns production systems end-to-end and cares about reliability, performance and design-first engineering. You thrive in fast-moving teams building AI platforms with real population-scale impact.
Requirements
- 3+ years building production backend systems
- Strong Python in production including asyncio and FastAPI or similar under real load
- Working knowledge of Go or strong willingness to learn it
- Experience building low-latency, multi-tenant backend services
- Hands-on experience with streaming systems including SSE or WebSockets and backpressure
- Strong PostgreSQL and Redis fundamentals including schema design and caching
- Comfort running services on Kubernetes in production
- Ownership mindset with testing, observability-driven debugging and RCAs
Lab profile
About Sarvam
Building India's full-stack sovereign AI platform across research, models, infrastructure and applications.
What they build
- Model API
- On-device AI
- Enterprise AI agents
Known for
- Sovereign AI focus for India
- Full-stack across research to applications
- Production deployment at banks, insurers and government
- Indian-language interactions at scale
Key facts
- Backed by Lightspeed, Peak XV and Khosla Ventures
Posted · Last seen