Sachin Beldona

Sachin Beldona is an engineer on the AI platform software team at NVIDIA, focusing on frameworks for LLM inference and libraries for LLM training. Sachin holds a M.S. in machine learning from Carnegie Mellon University, and a B.S. in computer science from University of Texas at Austin where he specialized in artificial intelligence and machine learning. Before joining NVIDIA Sachin worked at Capital One in the Financial Services AI Labs, working on agentic AI solutions for financial services customers.
Avatar photo

Posts by Sachin Beldona

Decorative image.
Developer Tools & Techniques

Creating the NVIDIA Nemotron 3 Ultra NVFP4 Checkpoint with NVIDIA Model Optimizer

As context windows grow longer, moving large model weights efficiently becomes critical to performance. A common way to address this is quantization, an... 16 MIN READ