Destava

Performance Engineer, Inference

Sarvam is hiring for Performance Engineer, Inference in Bengaluru. Senior level. First seen October 21, 2026; open as of November 12, 2026. Jobs taken straight from company career pages — no aggregator in between.

Save to applyRead more and apply on Sarvam's site

With Destava: How well do you fit? · Tailor my résumé · Write a cover letter

Company
Sarvam
Where
Bengaluru
Level
Senior
First seen
October 21, 2026
Listed via
Ashby

What the posting says

You will integrate artifacts from the model and kernel teams into a running multi-node, multi-tenant stack, and you will build and train your own speculators - draft models, distillation from the target, acceptance-rate tuning against the live serving distribution - rather than only wiring in stock implementations. You will produce, and defend, the latency and throughput numbers the company plans against, and you will spend significant time in cross-team work with architecture co-design, the kernels team, the model team, and SRE. Your scoreboard: TTFT (p50 / p95 / p99), TPOT, throughput, GPU…

Read more and apply on Sarvam's site

This page includes information from the O*NET 31.0 Database by the U.S. Department of Labor, Employment and Training Administration (USDOL/ETA). Used under the CC BY 4.0 license. O*NET® is a trademark of USDOL/ETA.