Winner. Scientist of the Year 2022

Amey Porobo Dharwadker

Academic title, degree: M.S. in Electrical Engineering
Fields of science: Artificial Intelligence
Research interest: Applied Machine Learning, Recommender Systems
Career Development: Experienced
Organization: Meta
Position: Machine Learning Technical Lead
City: San Jose, California
Country: USA

As a highly experienced technical engineering leader in Artificial Intelligence (AI) and Machine Learning (ML), Amey has made a remarkable impact on the industry over the course of his decade-long career. Currently, he serves as a Staff Machine Learning Engineer at Meta, leading the Facebook Video Recommendations Core Ranking team. His work involves the development of cutting-edge ML ranking algorithms to enhance the accuracy and effectiveness of video recommendations for billions of users worldwide. This work has been instrumental in driving the remarkable growth of active users on Facebook through the success of Facebook Watch, which reaches more than 1.25 billion users monthly (last publicly reported in September 2020).

Mr. Dharwadker’s exceptional cross-functional leadership skills have significantly contributed to solving the cold start problem for the Facebook Watch video recommender system. He utilized data from active users and popular videos in unique and effective ways to improve recommendation performance for tail users and videos, resulting in increased business value for Facebook. His notable achievements include his prior work on News Feed and Ads Ranking Machine Learning at Facebook, which resulted in a significant increase in user engagement and revenue for the company. Amey also filed a patent for his Comment Moderation technology, which aims to increase user control and protect against online bullying and harassment on social media. His contributions to Facebook News Feed have revolutionized the way billions of users discover and interact with relevant content on the platform. This was recognized through granting a patent and positive international media coverage. Prior to that, he demonstrated expertise in real-time image processing by developing computer vision-based Advanced Driver Assistance System algorithms for the automotive industry.

In addition to his technical contributions, Amey provides valuable leadership and mentorship to the team of ML engineers and data scientists, setting vision, strategy, and direction for large cross-functional projects. He is recognized as a well-regarded AI/ML expert in the industry due to his passion for advancing the field and ability to explain its complexities to others. This has led to him being featured in prominent technology publications, where he shares insights and advice on relevant topics in the field. In addition, he has served as a program committee member and reviewer for top-tier international conferences and journals in the field of Recommender Systems and Deep Learning, demonstrating his expertise in the area.

Amey holds a Bachelor's degree in Electronics & Communication Engineering from the National Institute of Technology Tiruchirappalli, India, and a Master's degree in Electrical Engineering with a specialization in Computer Vision and Machine Learning from Columbia University, USA.

Amey received the International Achievers' Award from Indian Achievers' Forum for his exceptional professional accomplishments and contributions. He was also awarded the Nationwide Award for Most Prominent Industry Expert of the Year in Machine Learning for leading change through technological innovation.

His research on addressing conformity bias and exploring user interests in recommender systems was accepted for publication as two papers at the prestigious ACM WebConf (WWW) conference, demonstrating the depth and specificity of his work.

As a thought leader in AI, Amey served as a jury member for the Edison Awards and a mentor at the Worldwide AI Hackathon, recognizing excellence, innovation, and innovators in the field. He was also invited to speak on various topics on recommender systems at ML Summits, such as RE-Work Enterprise AI Summit, MLConf, and Data Innovation Summit.

A Technical Leader of Facebook's Video Recommendations Ranking team, Mr. Dharwadker has driven breakthrough advancements in the company's video recommendation products. He leveraged neural modeling and multi-task learning to develop advanced recommender models that have been crucial in driving the success of videos and accounting for around 40% of the total global time spent on Facebook. His work has been recognized in international media. He also guides large cross-functional teams to achieve organizational goals through creating alignment effectively, coaching, mentoring, and influence.