Summary

I build ML infrastructure that runs on billions of devices.
Currently leading teams at Qualcomm working on LLM quantization and on-device AI deployment.

Previously,
Built AI Hub (SaaS platform) to enable model optimizations and deployment for edge.
Helped shape Apple's CoreML stack powering all on-device ML use cases in Apple ecosystem.
Worked on NVIDIA's optimizing and code-gen compiler that powers ML training and inference via CUDA.

I enjoy working at the intersection of compilers and machine learning - making models smaller, faster, and accessible to developers worldwide.

Work

Senior Engineering Manager, ML Platform

Nov 2023 - Present

Qualcomm

  • Leading state-of-the-art quantization tool AIMET; Bringing in advanced LLM quantization techniques
  • Shipping LLM quantization recipes with AIMET; Making them accessible to developers worldwide through AI Hub
  • Improving qualcomm developer workflow: quantization, compilation, debugging and deployment on Snapdragon
  • Performance optimizations: latency, memory footprint, graph infrastructure for GenAI

Founding Machine Learning Engineer

Aug 2022 - Nov 2023

Tetra AI (acquired by Qualcomm)

  • Launched AI Hub - first model zoo focused on on-device optimized models and deployment
  • Led Microsoft Teams AI use-cases; Segmentation, Audio, Video-Codec
  • Developed graph infrastructure and graph-to-graph transformations for iOS platform on CoreML Tools
  • Launched SaaS platform for model optimization and deployment

Senior Machine Learning Engineer, ML Platform

June 2019 - Aug 2022

Apple

  • Designed MIL intermediate language - core to all CoreML model deployment
  • Led ONNX-CoreML converter; Core contributor to CoreML Tools
  • Enabled Stable Diffusion and GenAI models on-device
  • Led auto-upgrade tool for model format migration; On-boarded Vision Pro

Intern, SPIR-V Compiler

May 2018 - Aug 2018

NVIDIA

  • Developed compiler optimization controller for phase ordering and parameter tuning

System Software Engineer, Compiler

Jun 2015 - Jul 2017

NVIDIA

  • LLVM compiler optimizations for Tegra Graphics and CUDA
  • DWARF 2.0 debug frame support for CUDA 9.0

Intern, Compiler

Jun 2014 - Apr 2015

NVIDIA

  • PBQP register allocator - improved 98% of graphics/compute use cases

Projects

AIMET

LLM quantization recipes, PTQ/QAT workflows

AI Hub Models

ML model zoo for on-device deployment

AI Hub Apps

Sample apps for Android, edge, and compute

AI Hub Workbench

Cloud platform for ML optimization

CoreML Tools

Apple's ML conversion stack

MIL

Model Intermediate Language

ONNX-CoreML

ONNX to CoreML converter

PyTorch

Open source contributions

Face Illumination

GANs for domain adaptation

Co-Operative GANs

Auto-ML for GAN training

Talks

On-device AI Use Cases SF AI Engineer Meetup 2025 Running ONNX models on-device ONNX Community Meetup 2025 Optimize & deploy models on-device DroidCon London 2024 Qualcomm AI Hub Workshop Embedded Vision Summit 2024 ML on Edge Devices Voxel51 Meetup 2024 Building AI powered applications MLOps Community

Education

MS Computer Science

Stony Brook University

2017 - 2019

BTech Computer Engineering

VIT Pune

2011 - 2015

Recognition

F8 Hackathon Finalist

Presented to Mark Zuckerberg

Huggingface Shoutout

DistilGPT-2 via onnx-coreml

GenAI Hackathon Judge

GenLab hackathon

Skills

C++ Python PyTorch LLVM ONNX CoreML TensorFlow Quantization Compilers On-device ML