Summary
Abhinav Sarje is a Member of Technical Staff in San Francisco with 15 years of experience building high-performance AI and HPC software, specializing in C/C++, MPI, OpenMP, CUDA and ROCm. He has led kernel and models teams at Tenstorrent and Cerebras, delivering optimized deep learning kernels and linear algebra on novel manycore and wafer-scale accelerators. Earlier roles at Lawrence Berkeley National Lab and Onera combined large-scale parallel simulations, ML for scientific discovery, and production-grade hybrid cloud data pipelines. Known as a dreamer, explorer and maker on GitHub, he blends research-grade numerical methods with production performance engineering. Notably, he has shipped kernels for million-core architectures and pursued autotuning and learning-based optimization to squeeze out parallel efficiency. He holds a PhD in Computer Engineering and consistently bridges academic rigor with applied systems work in vision and scientific AI.
15 years of coding experience
20 years of employment as a software developer
Doctor of Philosophy - PhD Computer Engineering, Doctor of Philosophy - PhD Computer Engineering at Iowa State University
Bachelor of Technology - BTech Computer Science, Bachelor of Technology - BTech Computer Science at Indian Institute of Technology, Guwahati
English