Summary
Rishi Thakkar is a Senior Deep Learning Software Engineer at NVIDIA with 10 years of experience specializing in accelerating inference on GPUs using CUDA, optimization techniques, and deep knowledge of GPU architecture through work on TensorRT. He blends software and hardware expertise acquired from ML implementation and profiling on GPUs and FPGAs at NCSA with hands-on systems and FPGA teaching roles at UIUC, giving him a rare full-stack perspective from silicon to production AI services. Rishi has built cloud-ready back-end systems and data pipelines earlier in his career, and he regularly applies that systems-thinking to squeeze latency and efficiency gains in real-world AI deployments—from cloud to self-driving applications. Colleagues describe him as organized, tenacious, and driven by practical problem-solving, with a longstanding interest in using engineering to make measurable impact.
10 years of coding experience
1 year of employment as a software developer
Bachelor of Science (BS), Computer Engineering, Bachelor of Science (BS), Computer Engineering at University of Illinois Urbana-Champaign
English, Spanish, Hindi