Performance Engineer, On-Device Inference

Sarvam; Bengaluru; On-site; INR 1,000,000 - 1,500,000; Full time

Job summary

Sarvam in Bengaluru is seeking an experienced ML model engineer to transform models into production-ready artifacts. You will partner with application teams and take ownership of model-chipset pairs for integration.

The ideal candidate will have 3+ years in ML systems, experience with PyTorch, and a solid background in quantization. Join us in pushing the frontiers of AI with real impact on a large scale.

Qualifications

• Minimum 3 years of experience in Machine Learning systems.
• Strong expertise in PyTorch with ONNX export.
• Experience in quantization of real models.

Responsibilities

• Quantize, validate accuracy, and document models.
• Integrate models with consuming app teams and debug issues.
• Maintain the team's benchmark harness.

Skills

Machine Learning Systems

PyTorch

ONNX

Quantization

Profiling

Tools

ONNX Runtime

TensorRT

CoreML

OpenVINO

QNN

LiteRT

Job description

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.