Hungryroot is using AI to build the most consumer-centric food and wellness company to ever exist. They are seeking a Senior Data Scientist to join their growing Data Science team, responsible for developing machine learning models that enhance customer personalization and engagement. The role involves designing robust feature representations, addressing cold-start problems, and driving rigorous experimentation to measure impacts on customer satisfaction.
Responsibilities:
- Separate durable preference from noise. Design robust feature representations from high-cardinality, implicit behavioral data (swaps, skips, saves) to capture true user intent and predict future engagement
- Model temporal dynamics and changing tastes. Architect sequential and recency-aware systems that adapt to shifting user preferences, ensuring recommendations reflect current intent rather than stale history
- Solve the cold-start problem. Leverage cohort signals, clustering, and content embeddings to generalize learnings across users, ensuring that even a new customer’s first box feels deeply personalized
- Bridge ML and constrained optimization. Integrate model scores (e.g., predicted conversion) with operations-research engines to perform business-aware re-ranking, balancing personalization with hard constraints like diet, budget, and inventory
- Advance the modeling. Evolve our systems using the architectures that drive modern, high-scale personalization, such as multi-stage retrieval and ranking, learning-to-rank (LTR), matrix factorization, and gradient-boosted trees. You will also evaluate and integrate more sophisticated techniques (like contextual bandits or sequence modeling) as our data complexity grows
- Drive rigorous experimentation. Define robust offline evaluation metrics (e.g., NDCG, MAP) and design online A/B tests to measure true causal impact on customer retention and satisfaction