Senior Machine Learning Engineer, Search & Recommendations

Instacart

1d•CA$180,000 - CA$190,000•Remote

About The Position

The Search & Personalization ML team at Instacart is responsible for developing a state-of-the-art multi-task, multi-objective ranking system that unifies search, discovery, recommendation, ads, and merchandising into a single value-aware platform. This team builds the core ranking infrastructure that influences every aspect of the user's shopping journey, optimizing for key business metrics such as incremental Gross Transaction Value (GTV), basket lift, and customer retention over the long term. Instacart is a Flex First company, offering employees the flexibility to work from home, an office, or other preferred locations, while fostering connection through regular in-person events.

Requirements

4+ years applying ML at scale with a Master’s degree, or 2+ years for PhD, with a proven track record improving ranking or recommendation systems in production.
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.
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.

Nice To Haves

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.

Responsibilities

Architect the ranking backbone that unifies query understanding, personalization, multi-objective ranking, ads, and merchandising into a single adaptive platform.
Design and build a search autosuggest system optimized for personalization and value-based relevance.
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.
Own the inference layer: goal-aware re-rankers, diversity and quality constraints, safe exploration, and millisecond-class latency optimization.
Advance evaluation practices: online experiments, long-horizon cohort metrics, counterfactual evaluations, and attribution pipelines for tracking incremental GTV and retention.
Partner across ads, infrastructure, product, and design teams to translate business goals into ranking policies and measurable ROI.
Mentor ML engineers to build expertise in ranking, causal inference, and scalable serving systems.