BENGALURU · FULLTIME
Performance Engineer, On-Device Inference
Sarvam AI
Bengaluru · onsite · Posted 58d ago
Sourced from
Not disclosed3–5 yrsfulltimeBengaluru
About a minute. You'll make an account on the way through.
agent · working
- Read this posting0.7s
- Found the form on Foundit · 9 questions to answer1.4s
- Decided the answers for all of them2.5s
- Tailor your résumé to this role
- Waiting for you
Section · 01
About this role
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
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.
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.
- 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.
- Custom op authoring in any runtime.
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
Sourced from foundit
Section · 02
Skills
LiteRTTensorRTOnnxONNX RuntimeCoreMLOpenVINOPytorchQNN
Section · Company
About Sarvam AI
Sarvam AI
Bengaluru
IN
About
Sarvam AI develops AI infrastructure, models, and applications designed to support Indian languages and enterprise use cases. Sarvam AI develops artificial intelligence infrastructure, models, and applications designed to support Indian languages and enterprise use cases. Its platform provides capabilities such as text-to-speech, speech-to-text, translation, document digitization, dubbing, and conversational AI through APIs and deployable products. The company builds and operates a full-stack AI ecosystem that includes foundational models, application-layer tools, and infrastructure for serving AI workloads at scale. Sarvam’s offerings are used by enterprises, government organizations, and developers to automate workflows, process multilingual content, and enable AI-powered interactions across diverse linguistic contexts. The company also develops language and multimodal models tailored to Indian languages and regional requirements, with support for deployment in cloud, private cloud, on-premises, and air-gapped environments.
Industries
Artificial Intelligence (AI)Generative AISoftware