Super Data Science: ML & AI Podcast with Jon Krohn 947: How to Get Hired at Top Firms like Netflix and Spotify, with Jeff Li
42 snips
Dec 9, 2025 
Jeff Li, a senior data scientist with experience at Netflix and Spotify, shares insights into working at top tech firms. He discusses the intricacies of forecasting and the tools used to achieve accurate predictions, like ARIMA and Prophet. Jeff emphasizes the importance of building a unique skill set for job applications and offers tips on landing roles at major companies. He also delves into his startup, yourmove.ai, designed to enhance dating experiences with AI while reflecting on the balance between automation and human input.
AI Snips
Chapters
Books
Transcript
Episode notes
Design For Reuse And Robustness
- Building for scale requires repeatable frameworks, naming conventions, and model ops like auditing and alerting.
- Move from hacky one-offs to reusable components to gain efficiency across many models.
Respect Time Order In Splits
- Do not randomly split time-series data; preserve time order when creating train/test sets.
- Use expanding or sliding windows for cross-validation to test model stability over time.
Interpretability Beats Complexity Often
- Stakeholders often need interpretable forecasts more than marginal accuracy improvements.
- Simple additive or GLM-style models remain valuable because they reveal assumptions and drivers.
