Infrastructure SRE - HPC
Sarvam · Bengaluru
CHECKED 18H AGO
Frontier labonsitesenior
At a glance
Highlights
- Operate a large multi-vendor GPU fleet serving training and inference together.
- Keep hundred-GPU training runs alive for weeks while protecting serving p99.
- Build internal reliability tooling and drive postmortems into durable fixes.
Ideal candidate
An SRE who thrives on on-call ownership of large GPU fleets and loves debugging hard systemic failures. You care about keeping both week-long training runs and latency-sensitive serving healthy on shared infrastructure.
Requirements
- 5+ years in infrastructure or SRE, including 2+ years operating GPU clusters at scale
- Demonstrated on-call ownership of critical infrastructure with postmortems driving durable fixes
- Proficiency in Python or Go to build and maintain internal tooling
- Working fluency across storage, fabric, GPU systems, Kubernetes and workload reliability with depth in one area
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