Principal Product Manager, Page Personalization Algorithms at Netflix
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Columbia University
Doctor of Philosophy - PhD, Computer Science
June 1, 2013 – May 1, 2014
Delft University of Technology
Doctor of Philosophy - PhD, Computer Science
January 1, 2011 – January 1, 2015
Florida Atlantic University
Master of Science - MS, Computer Science
September 1, 2009 – December 1, 2009
Universität Klagenfurt
Master of Science - MS, Computer Science
January 1, 2008 – January 1, 2009
Universität Klagenfurt
Bachelor of Science - BS, Computer Science
January 1, 2005 – January 1, 2008
Netflix
Principal Product Manager, Page Personalization Algorithms
August 1, 2023 – Present
San Francisco Bay Area
Netflix
Senior Product Manager, Search Algorithms
January 1, 2020 – August 1, 2023
San Francisco Bay Area
Bloomberg LP
Machine Learning Product Manager & Data Scientist, CTO Office
July 1, 2018 – January 1, 2020
New York, NY
Bloomberg LP
Machine Learning Software Engineer Tech Lead, Search & Discovery
September 1, 2015 – July 1, 2018
New York, NY
Research Intern
June 1, 2014 – September 1, 2014
New York, NY
Microsoft
Research Intern
September 1, 2011 – December 1, 2011
Beijing, China
Delft University of Technology
Researcher and Scientific Programmer
June 1, 2010 – June 1, 2011
Delft Area, Netherlands
Florida Atlantic University
Visiting Researcher
September 1, 2009 – December 1, 2009
Miami/Fort Lauderdale Area
Infineon Technologies
Software Engineer
February 1, 2006 – February 1, 2009
Klagenfurt, Austria
Predicting query failure using search engine logs and visual search results
December 1, 2011 – Present
Developed an algorithm able to predict when a query on a video search engine in the context of a user’s search session will fail, helping to more effectively deploy video search result optimization techniques. Predictions are based on features derived from the search log of the engine and from the visual and textual search results. Experiments indicate a 13% performance improvement over state-of-the-art baseline approaches.
Intent-Aware Video Search
June 1, 2011 – Present
* Identified useful intent categories for video search and demonstrated with a large crowdsourcing study the potential for these categories to improve video search. * Developed a video search result optimization algorithm to rearrange initial results list produced by YouTube with respect to the user’s intent. Experiments indicate a 34% performance improvement in satisfying users’ information needs compared to initially produced results lists.
SocialZap
June 1, 2011 – Present
Developed a system able to analyze tweets about TV shows to automatically provide non-linear video access and to enrich the video with user-contributed information.
Near2Me
June 1, 2010 – Present
Developed Near2me, a travel recommender system for off-the-beaten-track destinations. Evaluated the system with a task-directed walk-through of frequent travelers, showing its effectiveness.
Reading Between The Tags
June 1, 2010 – Present
Developed an approach for improving the informativeness of image tags by predicting whether a tag denotes a physical entity and what real-world size class (small, medium, large) this entity has. Experiments demonstrated the effectiveness of the approach and showed a 29% increase in correct predictions over standard baseline systems.
Intent Taxonomy for Image Search
April 1, 2010 – Present
* Developed a first version of a user intent classification scheme for image search. Derived features from search sessions allowing to classify a user’s intent, outperforming standard approaches. * Developed an algorithm able to adapt Flickr’s result view based on the predicted intent of a user.
Index Strategy Evaluation for Content-Based Image Retrieval
March 1, 2009 – Present
Evaluated Locality Sensitive Hashing and R* trees as indexing strategies for content-based image retrieval for the Lucene Image Retrieval library. Experiments indicated an increase in efficiency with no decrease in accuracy of the search results.
Cultural Fit Analysis
The candidate has worked at prominent tech companies (Netflix, Bloomberg, Google, Microsoft) and academic institutions, indicating adaptability to diverse high-performance environments. Their project history shows a strong inclination towards innovation and research, which aligns well with companies that value R&D. However, the recent shift to primarily product management roles might suggest a different career trajectory than a hands-on Backend Engineer, potentially impacting cultural fit for a purely engineering-focused team without product responsibilities.
Soft Skills & Operational Fit
The candidate's career progression from Software Engineer to Machine Learning Tech Lead and then to Principal Product Manager at top-tier companies suggests strong leadership, problem-solving, and strategic thinking skills. Their extensive research background indicates a methodical and analytical approach to challenges. The transition to product management roles, while valuable, might require re-evaluation of current hands-on coding proficiency for a pure Backend Engineer role.