Tejaswin Parthasarathy
Postdoctoral Scientist at NVIDIA
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolTejaswin Parthasarathy is a postdoctoral scientist and DL inference engineer with eight years of experience building high-performance simulation and production software that accelerates scientific discovery and real-world AI workloads. Based in the Bay Area, he splits his time between NVIDIA’s TensorRT team optimizing LLM and vision inference and academia at UIUC, where he develops HPC codes and mentors interdisciplinary PhD students. His PhD yielded 14 publications, two open-source codes, and experimental translations of simulation-driven device designs—highlighting a rare ability to move from algorithm and continuum-mechanics theory to hardware prototypes. He combines rigorous academic training (PhD, UIUC; IIT Madras undergraduate) with hands-on systems engineering, making him equally comfortable tuning GPU inference pipelines and writing scalable scientific DSLs. Notably, he balances production-grade deployment work with ongoing open-source and mentoring commitments, bridging research impact and industrial-scale performance.
9 years of coding experience
Indian Institute of Technology MadrasKendriya Vidyalaya SangathanHigh School, 94.6% (12th grade), High School, 94.6% (12th grade) at Maharishi Vidya Mandir, ChennaiDoctor of Philosophy - PhD, Mechanical Engineering, 4.0/4.0, Doctor of Philosophy - PhD, Mechanical Engineering, 4.0/4.0 at University of Illinois Urbana-Champaign
Github Skills (33)
torchscript10
simulation10
pytorch10
runtimes10
python10
jetson10
tensorrt10
inference10
large-language-models10
nvidia10
libtorch10
mechanics10
cuda10
elastica10
cpp10
Programming languages (5)
Github contributions (5)
tp5uiuc/kinematic_snake
Dec 2019 - Jan 2022
Contributions:78 commits in 2 years 1 month
tp5uiuc/elastica-pipelines
Aug 2022 - Oct 2023
Pipelines for Elastica++ applications
Contributions:237 reviews, 88 PRs, 50 pushes in 1 year 1 month
pipelineselasticaelasticsearch
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.