Harsh Sharma

I'm an ML Engineer at NVIDIA, in AI for Media, working on human motion models and agents.

At NVIDIA, I work on:

(1) Generative 3D human pose and mesh recovery, from research model to shipped SDK - Check out SOMA-X
(2) Large-scale evaluation across real and synthetic benchmarks
(3) LLM and vision-language post-training, SFT/LoRA fine-tuning, and adversarial evaluation of agents
(4) CUDA-accelerated inference for real-time AI video, at scale
(5) Motion analytics in sports from mesh recovery — shown at NAB Show

I completed my Master of Science in Robotics Systems Development from Carnegie Mellon University's School of Computer Science (2021), where I focused on Computer Vision and SLAM. Before grad school, I worked at CMU (2018-19) on the DARPA SubT Challenge and collaborated with the Culinary Institute of America on skills evaluation using HMMs.

Prior to CMU, I was one of the early engineers at Addverb Technologies, a robotics startup that was acquired by Reliance for $132 million. At Addverb, I worked on the full stack for warehouse autonomous robots—from perception to path planning—and helped recruit the founding engineering team. The company quickly scaled to serve major clients like Patanjali, ITC, and Coca-Cola. I graduated from IIT Indore (2017) with a BTech in Mechanical Engineering, focused on ML, Computer Vision, and Mechatronics.

The best way to reach me is via twitter. DM me and let's just grab coffee. More here:
Email GitHub LinkedIn Twitter Substack