Software Engineer - Model API Platform Engineering
Sarvam · Bengaluru
Frontier labonsitesenior
At a glance
Highlights
- Own model APIs handling tens of millions of calls daily.
- Drive sub-100ms latency across real-time AI pipelines.
- Build streaming speech pipelines serving enterprises at scale.
Ideal candidate
Latency-obsessed backend builder who thrives owning critical systems end to end. You ship fast, reason from first principles, and default to AI to move faster.
Requirements
- 4-6 years building and operating production backend systems
- Owned at least one service end to end under real load
- Strong distributed-systems fundamentals including concurrency, networking, queues, caching and failure modes
- Experience with low-latency or high-throughput services and p95/p99 reasoning
- Solid fundamentals with PostgreSQL and Redis including schema design and caching strategy
- Fluency in at least one backend language and willingness to work in Python and Golang
- Experience with containers, CI/CD and production monitoring
- Daily hands-on use of AI tools in engineering workflow
- Bias for action and clear RFC and design-doc writing
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