Summary
Sagar Desai is a Senior Solutions Architect at NVIDIA with 6+ years of hands-on experience building end-to-end ML and MLOps solutions, now focused on accelerated generative AI, training/inference pipelines, and continuous learning across NVIDIA’s AI stack. He has a strong track record in LLMs, agents, quantization (AWQ/GPTQ), vLLM/TensorRT-LLM and RAG systems from his prior MLOps role at Fractal, where his agent framework and Hugging Face activity earned community recognition. Earlier roles in automotive and manufacturing applied ML to CAE and analytical engineering, giving him uncommon depth in physical system modeling combined with modern ML deployment. He actively publishes and prototypes on GitHub and Hugging Face — notable projects include agent_llm_dev, graph_chat, quantized Vicuna builds and RL work — demonstrating a blend of research, productionization and experimentation. Sagar holds an ML/AI postgraduate diploma from IIIT Bangalore and an MTech in Design, which underpins his habit of pairing rigorous engineering with continuous learning. He’s known for reducing model build/debug time and automating non-standard pipelines, translating research ideas into robust, resource-efficient production systems.
5 years of coding experience
8 years of employment as a software developer
Postgraduate Diploma in Machine Learning and Artificial Intelligence, Postgraduate Diploma in Machine Learning and Artificial Intelligence at International Institute of Information Technology Bangalore
Master of Technology (MTech) Design, Master of Technology (MTech) Design at Vishwakarma Institute Of Technology
Bachelor of Engineering (B.E.) Mechanical Engineering, Bachelor of Engineering (B.E.) Mechanical Engineering at Shivaji University
Kannada, Hindi, Marathi, English