Nitin Pasumarthy
Staff Software Engineer, Applied Machine Learning at LinkedIn
Sunnyvale, California, United States
Summary
👤
SeniorNitin Pasumarthy is a Staff Software Engineer specializing in applied machine learning at LinkedIn with 12 years of software engineering experience and a focused two-year track record in ML research and deployment. He designs scalable optimizations across content delivery pipelines that impact LinkedIn’s front- and back-end user-facing systems, blending production engineering rigor with research experimentation. Comfortable across SQL, JavaScript, Python and Java, he bridges web development and ML productionization, bringing prior startup through multinational experience to large-scale problems. Beyond product work, he contributes to open-source ML projects—most recently improving model training, hyperparameter tuning, and experiment tracking for the high-profile Therapeutics Data Commons repository—demonstrating a knack for reproducible experimentation. Based in Sunnyvale, he pairs practical frontend chops with deep-learning certifications and a pragmatic focus on deployable, measurable ML outcomes.
12 years of coding experience
Stackoverflow
7,447reputation
1.8mreached
21answers
30questions
postgresql
top-1%
google-api
top-5%
firebase-realtime-database
top-5%
macos
top-1%
firebase
top-5%
javascript
top-5%
Github Skills (26)
pytorch10
postgresql10
python10
machine-learning10
deep-learning10
macos10
google-api9
javascript9
mlflow9
firebase-realtime-database9
drug-discovery9
firebase9
data-analysis8
pandas8
artificial-intelligence7
Programming languages (16)
Github contributions (5)
mims-harvard/TDC
Nov 2022 - Nov 2022
Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science
Role in this project:
ML Engineer
ML EngineerContributions:2 reviews, 5 commits, 1 PR in 7 days
Contributions summary:Nitin's contributions center on developing and refining a machine-learning model within the Therapeutics Commons (TDC) repository, focusing on the hERG inhibition toy model. The commits demonstrate work on preparing the data, training the model, and parsing training logs to prepare for Ray Tune and MLflow integration. The code changes involve modifications to existing notebooks and the creation of functions to facilitate hyperparameter optimization and experiment tracking, aligning with the goal of enhancing model performance and reproducibility.
multimodalmachine-learningtherapeuticsdrug-discoverydatasets
linkedin/performance-quality-models
Dec 2021 - Nov 2022
Personalizing Performance model repository
Contributions:9 commits, 2 PRs, 5 pushes in 11 months
tensorflowjsmachine-learningmodel-performanceperformancetensorflow
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.