Senior Machine Learning Engineer (Search & Recommendations Ranking)

Join Instacart as a Senior Machine Learning Engineer, where you'll work on the Search & Recommendations ML team. You'll architect the ranking backbone that powers the shopping journey, design long-horizon objective functions, develop production-grade Multi-Task Learning, and own the inference layer. You'll also advance evaluation practices and partner with various teams to translate business goals into ranking policies. This role requires 5+ years of experience in applying ML at scale, strong coding and data fluency, and expertise in multi-task learning architectures.

• Architect the ranking backbone that unifies query understanding, personalization, multi-objective ranking, ads, and merchandising into a single adaptive platform.
• Design long-horizon objective functions (e.g., incrementality, LTV, habit formation) and build uplift/causal value models that move beyond short-term engagement.
• Develop production-grade Multi-Task Learning (e.g., shared encoders, MMOE/PLE task heads) to jointly learn relevance, propensity, margin, and churn risk—ensuring calibration, constraints, and explainability.
• Demonstrated success in applying multi-objective or constrained optimization to balance relevance, revenue, margin, and user experience; experience with online testing and attribution beyond CTR
• 5+ years applying ML at scale (3+ years in technical leadership), with a proven track record improving ranking or recommendation systems in production
• Strong coding (Python) and data fluency (SQL/Pandas), with expertise in classic ML techniques (e.g., XGBoost) and deep learning frameworks (TensorFlow/PyTorch)
• Excellent analytical skills and strong cross-functional communication abilities
• Expertise in multi-task learning architectures (e.g., MMOE/PLE, shared encoders), calibration, counterfactual evaluation, uplift/causal modeling, and/or contextual bandits for exploration
• Experience building low-latency ranking services, including feature stores, caching, vector + lexical retrieval, re-ranking, and A/B testing infrastructure, with expertise in constraint-aware inference
• Hands-on experience with LLMs as feature/recall enhancers (e.g., embeddings, adapter tuning) while maintaining clarity on when the ranker should arbitrate