Skip to main content

Performance Engineer, On-Device Inference at Sarvam

Department: Infrastructure

Setup
On-site
Location
Bengaluru, Karnataka
Level
mid
Posted

Description

Sarvam is hiring an ML Systems Engineer to take models from research handoff to production-ready artifacts across at least two target chipsets, including Intel xPU, ARM xPU, Apple xPU, and Nvidia or AMD GPUs. The role owns one or two model-chipset pairs end-to-end, quantizes and validates accuracy, benchmarks and documents deployments, maintains the benchmark harness, and debugs performance and accuracy issues with consuming application teams.

For job seekers

Ready to find a role that actually fits?

Upload your résumé, start a Job Search Thread, and let Metaintro rank real openings against your experience — then guide you from search to offer.

Match

Compare live roles against your current evidence.

Position

Turn proof projects into role-specific applications.

Improve

Use market feedback to keep the skill plan current.

Return to navigation