Summary
Sujay Khandagale is a Staff Machine Learning Engineer in San Francisco with nine years of experience building production ML systems and publishing research-grade evaluations. He has advanced recommender and search models at Abacus.AI, led ML initiatives at Pinterest, and now drives ML engineering at Coupang, combining transformer-based two-tower architectures with pragmatic production improvements. His work spans extreme multi-label classification, robustness to distribution shift, feature-attribution benchmarking, and practical computer vision deployments—often turning research insights into scalable systems. Notably, he produced the first large-scale RecSys study accepted at NeurIPS and developed synthetic benchmarks for attribution methods, reflecting a rare mix of empirical rigor and engineering delivery. Trained at Columbia and IIT Mandi with research stints in Europe, he brings multilingual/NLP and applied vision expertise to cross-domain ML challenges.
10 years of coding experience
7 years of employment as a software developer
Exchange Student, Computer Science, Exchange Student, Computer Science at Aalto University
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at Columbia University
Bachelor of Technology (B.Tech.), Computer Science, Bachelor of Technology (B.Tech.), Computer Science at Indian Institute of Technology, Mandi
English, German, Marathi, Hindi