I’m a recommender systems engineer.
I help data scientists and machine learning engineers bridge the gap between modeling and serving recommendations, so that they can spend less time worrying about infrastructure and more time improving the recommendations they make.
Over the course of my career, I’ve done web development, back-end service development, data engineering, analytics engineering, and machine learning in languages like Python, Ruby, Scala, and Javascript. With this range of experience, I’ve become a “deep generalist”—I’m specifically focused on recommender systems, which has allowed me to delve deeply into what makes recs work (and fail!), but I also have relevant background to work on every part of the recommendations problem from the models to the front-end and back again.
Among my coworkers, I’m known for seeing how all the pieces fit together, making major changes as a series of incremental steps in the right general direction, and doing a ton of pairing with other developers. If you want to understand how I work and think about software development, I highly recommend GeePaw Hill’s Many More Much Smaller Steps series.
Outside of work, I’m a cyclist, dog person, and video gamer. I’ve spent an inordinate amount of time managing space colonists while they carve out a home for themselves on asteroids, both hospitable and…less so. My partner and I have also been semi-serious Overwatch players for the past five years. It is not a coincidence that these games are both about teamwork!
I also run the Mastodon social network instance recsys.social.
Karl Higley, Even Oldridge, Ronay Ak, Sara Rabhi, and Gabriel de Souza Pereira Moreira. In Proceedings of the 16th ACM Conference on Recommender Systems (RecSys ‘22). Association for Computing Machinery, New York, NY, USA, 632–635.
James McInerney, Benjamin Lacker, Samantha Hansen, Karl Higley, Hugues Bouchard, Alois Gruson, and Rishabh Mehrotra. Explore, Exploit, and Explain: Personalizing Explainable Recommendations with Bandits. In Proceedings of the 12th ACM Conference on Recommender Systems (RecSys ‘18). Association for Computing Machinery, New York, NY, USA, 31–39.