Summary
Arnav Komaragiri is a Research Scientist based in San Jose with eight years of hands-on experience building low-latency, production-ready ML systems and tooling. His work spans compute efficiency, multi-agent systems, reasoning, and multimodality, with a track record at NVIDIA and prior roles accelerating inference (sub-0.1s) and scaling model deployment using TensorRT, ONNX, Triton and FAISS. He has delivered practical transformer-based recommendation prototypes that cut design time and used synthetic-data computer vision to bridge sim-to-real gaps, combining research rigor with product-focused iteration. Known for squeezing redundant computation out of pipelines, he pairs deep engineering chops with curiosity—his GitHub motto, “i try to build cool stuff,” reflects a bias toward fast experimentation and tangible impact.
8 years of coding experience
3 years of employment as a software developer
High School Diploma General Studies, High School Diploma General Studies at William Mason High School
Computer Science Computer Science, Computer Science Computer Science at University of Cincinnati - College of Engineering and Applied Science