Summary
Mayank Kaushik is a senior engineering leader with 12+ years of hands-on experience architecting high-performance deep learning inference software for NVIDIA and Intel, now leading Deep Learning Inference Software across RTX and Data Center GPUs. He combines low-level expertise in OS internals, device drivers and parallel programming with system-level knowledge of computer architecture and inference frameworks to scale AI from desktop GPUs to cloud data centers. His teams ship flagship products like TensorRT-LLM, TensorRT-RTX and TensorRT-Cloud while contributing to ONNX and open-source tooling, reflecting a pragmatic balance of product delivery and community impact. An MBA from Berkeley complements his technical background (MS Computer Engineering, UT Austin), giving him a rare ability to translate chip bring-up tradeoffs into business and platform strategy. Not obvious from titles: he’s consistently been involved in chip bring-up, simulators and debugger tooling since his early NVIDIA days—skills that inform his low-latency, efficiency-first approach to AI inference.
12 years of coding experience
19 years of employment as a software developer
MS, Computer Engineering, MS, Computer Engineering at The University of Texas at Austin
Master of Business Administration (M.B.A.), Master of Business Administration (M.B.A.) at University of California, Berkeley, Haas School of Business
BE, Electronics and Communication, BE, Electronics and Communication at Delhi College of Engineering
High School, Science, Computers, High School, Science, Computers at Delhi Public School - R. K. Puram