ML/AI Operations

Hop maintains ML/AI systems in an ongoing manner

Here at Hop, we build and maintain machine learning infrastructure to enable existing research and product teams to be more effective in their work.

This often involves setting up compute and storage infrastructure for both raw data and features, as well as systems to track experiments and enable reproducible research. Our operations team members are motivated by efficiency, reproducibility and productivity.

Although bespoke solutions are sometimes necessary, we prefer to assemble them from well-understood (and preferably open-source) parts: Docker, Postgres, Kubernetes/Slurm, Metaflow/Airflow, Databricks, Weights and Biases, etc. 

Featured Case Study

Gobble, a pioneering meal kit delivery service, approached us with an interesting challenge: could we improve key business metrics – customer satisfaction, sales, and churn – by enhancing the quality of their weekly meal recommendations? There was an existing recommendation system that had served Gobble well so far, but it hadn’t kept up with their operational evolution over the years. Exciting product changes required fresh thinking, and the recommendation system was just the first of several key areas in which Gobble was hoping to deploy ML.

Are you looking to maintain your ML/AI systems efficiently? Contact us to learn how Hop can help.