Posted 5 Oct · 40 open roles
Performance Engineer, On-Device Inference
BengaluruonsiteApply by 26 Oct 2026
- Undisclosed
- Salary
- 3+ yrs
- Experience
- Full time
- Job type
Skills this role mentions
- Go
About the role
Take Sarvam models from research-handoff state to production-ready artifacts on at least two of our target chipsets (Intel xPU, ARM xPU, Apple xPU, Nvidia / AMD GPUs). You'll own 1 - 2 (model, chipset) pairs end-to-end and partner with the consuming app team during integration.
- Quantize, validate accuracy, benchmark, and document. Author the deployment workbook for each pair you own.
- Embed part-time with consuming teams during integration; debug perf and accuracy issues alongside them.
- Maintain and extend the team's benchmark harness.
- Solid PyTorch + ONNX export experience including the gotchas (dynamic shapes, control flow, custom ops).
Full details and the application are on Sarvam AI's careers site.
ATS resume check
Does your resume cover what this role asks for?
Many employers screen resumes automatically. Compare yours against this posting before you apply.
Sarvam AI
40 open roles
What tech interviews usually cover
Common rounds for engineering roles. Every company runs its own process.
The Sarvam AI name and trademarks belong to Sarvam AI. This listing summarises Sarvam AI's public job posting on Sarvam AI careers, and applications go directly to Sarvam AI. Jobsearchers is an independent job platform and is not affiliated with or endorsed by Sarvam AI; always check the details on the original posting. Report a problem.