Performance Engineer, On-Device Inference
Sarvam AI
Performance Engineer, On-Device Inference at Sarvam AI is a full time role based in Bengaluru, Karnataka, India. It was published on 4 June 2026 and was open at last check.
| Role | Performance Engineer, On-Device Inference |
|---|---|
| Company | Sarvam AI |
| Location | Bengaluru, Karnataka, India |
| Employment type | Full Time |
| Published | 4 June 2026 |
| Status | Open at last check |
About Sarvam
Sarvam is building the bedrock of Sovereign AI for India. The company is developing India’s full-stack sovereign AI platform, building across research, models, infrastructure and applications with a singular focus on making AI genuinely work for India. Sarvam works with leading enterprises and public institutions and is backed by Lightspeed, Peak XV, and Khosla Ventures. Sarvam partners with India’s leading brands, including Tata Capital, SBI Life, CRED, IDFC, and LIC.
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.
What You’ll Do
- 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.
What We're Looking For
- 3+ years on ML systems.
- Solid PyTorch + ONNX export experience including the gotchas (dynamic shapes, control flow, custom ops).
- Quantization in production on at least one real model.
- Comfort with at least two of: ONNX Runtime, TensorRT, CoreML, OpenVINO, QNN, LiteRT.
- Profiling fluency on at least one platform.
Bonus Points
- Custom op authoring in any runtime.
Why Sarvam?
Sarvam is a fast-moving, high talent-density team building full-stack AI for India, working on problems that push the frontiers of AI with real population-scale impact.
- Work alongside researchers, engineers, builders, and business leaders who move fast and hold each other to a very high bar
- High ownership and high impact, from day one
- Everything we do is AI-first, from the way we build and ship to the way we think about problems
- You can work on problems that could change how an entire country learns, works, and communicates
If you want to work on problems at the frontier of AI in India, Sarvam is the place to be.
Create your free OnJob profile to apply — we'll take you to Sarvam AI's application after sign-up. · Posted 4 Jun 2026.
Performance Engineer, On-Device Inference at Sarvam AI — questions answered
What does the Performance Engineer, On-Device Inference role at Sarvam AI pay?
Sarvam AI does not publish a salary on this Performance Engineer, On-Device Inference listing, so OnJob shows no figure for it rather than an estimate. For what this role pays across the market, the OnJob salary guides aggregate the live listings that do disclose pay.
Where is the Performance Engineer, On-Device Inference role at Sarvam AI based?
Sarvam AI lists this Performance Engineer, On-Device Inference role in Bengaluru, Karnataka, India, advertised as full time work at that location. Larger employers sometimes cover several sites under one city name, so confirm the exact office with Sarvam AI before you apply.
Is the Performance Engineer, On-Device Inference role at Sarvam AI still open?
The Performance Engineer, On-Device Inference posting at Sarvam AI was open at OnJob's last check of the employer's careers page, having been published on 4 June 2026. OnJob re-checks source listings on each build and marks a role closed once it disappears, but listings can close without notice, so the employer's own page is the final word.
How do you apply for the Performance Engineer, On-Device Inference role at Sarvam AI?
Apply to the Performance Engineer, On-Device Inference at Sarvam AI role through OnJob with a free profile: OnJob scores your fit against the listing, shows the skills lowering that score, and submits an ATS-ready profile to Sarvam AI's own application page. Creating a profile is free and needs no card.
Related Engineering jobs
Hand-picked roles that match this listing on skills, category and location — each scored to your profile inside OnJob.
Explore more on OnJob
Hiring for a role like this?
Post a job on OnJob and reach AI-matched candidates.
