Performance Engineer, Inference is open at Sarvam in Bengaluru. Posted on Aug 10, 2026, and still on Sarvam’s careers page when we last checked, on Nov 14, 2026.
About the role
You will own Sarvam's production serving path for large distributed models end to end. You should be source-level fluent in at least one of SGLang, vLLM, NVIDIA Dynamo, or TensorRT-LLM - able to read and modify it where stock behavior does not fit our workloads - and you should operate and extend a distributed-serving stack at depth: disaggregated prefill-decode across nodes, distributed KV/cache transfer, and the…
The opening lines of the posting. The rest is on Sarvam’s careers page.
Hiring at Sarvam
Sarvam has 50 open roles right now. Most are in Engineering, Marketing & Community and Data & Research. See all its roles
