Mucun Tian - Applied Scientist at Amazon

Mucun Tian

Applied Scientist at Amazon

San Francisco Bay Area United States

Join Prog.AI to see contacts

Summary

👤

Senior

🎓

Top School

Mucun Tian is an applied scientist with nine years of experience building and scaling information retrieval, recommender systems, and causal inference solutions for consumer products, currently based in the San Francisco Bay Area and now at Amazon. He has led technical roadmaps and cross-functional teams to modernize search and ranking systems—shipping cloud-native MLOps pipelines and LLM-based search prototypes that cut iteration times from months to days. His research-driven approach produced novel counterfactual multi-task learning-to-rank models and practical bias-correction methods for offline evaluation, informed by hands-on implementation of Hierarchical Poisson Factorization in the open-source LensKit recommender toolkit. Comfortable in both research and production engineering, he blends deep statistical thinking with backend system design to turn evaluation insights into measurable online lifts.

9 years of coding experience

8 years of employment as a software developer

Master of Science - MS Computer Science, Master of Science - MS Computer Science at Boise State University

Bachelor's degree Electrical Electronics and Communications Engineering, Bachelor's degree Electrical Electronics and Communications Engineering at Sichuan University

Master of Engineering - MEng Signal and Information Processing, Master of Engineering - MEng Signal and Information Processing at Chengdu University of Information Technology

Github Skills (8)

javas10

model-building10

java10

recommender-system10

linear-algebra9

machine-learning9

algorithms9

performance-optimization8

Programming languages (2)

JavaPython

Github contributions (5)

lenskit/lenskit

Mar 2017 - Nov 2017

LensKit recommender toolkit.

Role in this project:

Back-end Developer

Contributions:61 commits, 2 PRs, 30 comments in 8 months

Contributions summary:Mucun's commits primarily involve the implementation of core functionalities and the addition of new classes within the `lenskit-pf` package. Specifically, the user added and refactored classes related to the build and initialization of the HPF model and its components. These changes included parameter definitions, data splitting strategies, and the overall structure of the HPF recommender. The user was focused on the integration of Poisson Factorization within the Lenskit recommender toolkit.

lenskitrecommenderjavarecsys

KimuraTian/lenskit

Feb 2017 - Nov 2017

Contributions:2 PRs, 85 pushes, 4 branches in 8 months

pythonrecommendermachine-learning

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.

Request Free Trial