Shishir Kumar
Senior Data Scientist
San Francisco, California, United States
Summary
👤
Senior🎓
Top SchoolShishir Kumar is a Senior Data Scientist with 8 years of experience building and deploying end-to-end ML solutions that improve operational efficiency and business outcomes. Based in San Francisco, he has deep expertise in gig-economy optimization at Shipt—designing geo-driven effort metrics, production models for pay policy, and fraud detection systems that reduced engineering effort and accelerated testing cycles. Earlier roles span large-scale transaction processing and automation at Loylty Rewardz, analytics for grocery fulfillment and experimentation at Factspan, and routing optimization for Recology, demonstrating strengths in SQL, Python, and scalable data engineering. He pairs practical product sense—winning stakeholder buy-in and shipping dark-mode production tests in days—with strong technical rigor from implementing ML algorithms from scratch during his MS in Data Science. Notably, he scaled pipelines to process billions of transactions and has a habit of turning messy geo and sparse-data problems into reliable modeling ground truth. His long-term focus is on building scalable, impactful products that make marketplaces and everyday services more efficient and fair.
8 years of coding experience
8 years of employment as a software developer
Master of Science - MS Data Science, Master of Science - MS Data Science at University of San FranciscoBachelor of Technology - BTech Chemical Engineering, Bachelor of Technology - BTech Chemical Engineering at Indian Institute of Technology, Kharagpur
Github Skills (10)
reinforcement-learning4
google3
recommender3
simulation3
recommender-system2
tensorflow2
machine-learning2
artificial-intelligence2
python2
deep-learning1
Programming languages (2)
Github contributions (5)
ShishirKumar93/linear-regression-project
Oct 2019 - Feb 2024
Contributions:6 pushes, 1 branch in 4 years 4 months
collinprather/SlateQ
Jun 2020 - Jun 2020
A comparison of Google SlateQ algorithm with traditional Reinforcement Learning algorithms
Contributions:21 commits, 21 pushes in 7 days
reinforcement-learning-algorithmstraditionalreinforcement-learningcomparisonlearning-algorithms
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.