Nishant Thakur

Nishant Thakur is an AI/ML engineer with 15 years of industry experience and a Master of Data Science. He works as a Senior Computer Scientist at Adobe, where he builds browser-native AI inference pipelines using WebGPU, ONNX, and WebAssembly. Most of his current work centers on making LLMs run locally: in the browser, on Apple Silicon, and without cloud dependencies. His Code Mode research, which cuts LLM tool-calling token overhead by 85% while doubling tool-selection accuracy, was presented at Adobe Bangalore Developer Day 2026 alongside a demo of a fully local PDF-to-podcast pipeline built on MLX. He speaks regularly at AI and developer meetups across Bengaluru, including MLX India.