Speaking & Teaching

Official CVPR tutorials, invited talks and hands-on instruction on production GenAI, Edge AI, model compression and deploying neural networks under real constraints.

Invite Anuj to speak
CVPR 2025
June 2025
Nashville, TN

Demonstrator

Deploying Multi-Modal Models in Edge AI Devices

CVPR 2025A live technical demonstration of multimodal AI deployment on edge hardware, included in the official CVPR demonstration program.

Decoding the Giants: Unveiling the Mysteries of Large Language Models presentation
October 2024
Virtual

Invited speaker

Decoding the Giants: Unveiling the Mysteries of Large Language Models

International Institute of Business AnalysisA technical session on how LLMs evolved, what they can do, where they fail, and the considerations teams face when putting them to work.

Edge AI in Action: Practical Approaches to Developing and Deploying Optimized Models presentation
June 2024
Seattle, WA

Co-organizer & instructor

Edge AI in Action: Practical Approaches to Developing and Deploying Optimized Models

CVPR 2024Co-created and delivered an official 3.5-hour tutorial on taking models from research to production under fixed memory, latency and hardware constraints.

Model Compression Techniques for Edge AI
September 2023
Santa Clara, CA

Conference speaker

Model Compression Techniques for Edge AI

AI Hardware & Edge AI SummitQuantization, pruning and knowledge distillation in practice: which techniques survive contact with real hardware, and what each one actually costs in accuracy.

Deploying TFLite Model with Flutter
2020
Chandigarh, India

Workshop instructor

Deploying TFLite Model with Flutter

ML ChandigarhA hands-on workshop taking a TensorFlow Lite model from training to a running Flutter app on both Android and iOS.

Deploying Machine Learning Models Efficiently on Mobile Devices presentation
May 2019
Cambridge, MA

Speaker & instructor

Deploying Machine Learning Models Efficiently on Mobile Devices

General Assembly / Boston New TechnologyA practical session on deployment constraints, optimization choices, and the trajectory of machine learning on mobile hardware.

Machine Learning Inference on Mobile Devices
January 2019
Cambridge, MA

Meetup speaker

Machine Learning Inference on Mobile Devices

Deep Learning in Production MeetupWhat changes when inference moves from a server to a phone — memory, latency, battery, and the optimization strategies that matter most.

Teaching & technical service

Helping other people build.

I have taught practical ML deployment, advised an institutional program and helped practitioners resolve model-development problems in public technical communities.

Program Advisor

UC Irvine · Customer Experience Certificate Program

Advised on customer-focused innovation and using data to accelerate and improve decisions.

Instructor

General Assembly

Taught practical on-device machine learning across mobile and embedded platforms, from model training through deployment.

Community Mentor

PyTorch Forums

Helped practitioners resolve PyTorch and model-development issues across training, architectures, debugging, performance and implementation.

Co-organizer

TensorFlow User Group Chandigarh

Helped organize a practitioner community for talks and workshops spanning TensorFlow, mobile ML and production deployment.