Senior Data Scientist

About the role

Instacart is seeking a Senior Data Scientist to own the end-to-end analytics and experimentation strategy that powers how we interpret customer intent and connect it to the most relevant items and retailers. In this role, you will define guardrails, monitor performance across platforms and segments, and diagnose conversion gaps to ensure search drives meaningful business outcomes. You will translate complex, noisy signals into clear insights and recommendations that move core metrics such as search conversion, order rate, and Gross Transaction Value. You will partner closely with Product, Engineering, and Machine Learning to shape the roadmap for search relevance, ranking quality, and latency. Your work will strengthen downstream experiences like ads and retailer satisfaction by building deep diagnostic analyses across key dimensions. You will improve data quality, instrumentation, and metric definitions so that teams can reason about performance with clarity, consistency, and speed. You will connect offline model evaluation with online and business metrics to ensure model changes reliably improve the end-user experience.

Key facts

What you'll do

• Own core Search metrics and funnels end to end (e.g., query → impression → engagement → cart adds), including defining guardrails, monitoring performance across platforms and segments, and diagnosing conversion gaps.
• Design, run, and interpret experiments across ranking, retrieval, and search UX (e.g., relevance model changes, query understanding, result layouts), turning ambiguous or conflicting outcomes into crisp, data-driven recommendations.
• Partner with Product, Engineering, and ML to prioritize opportunities, size impact, and influence the roadmap for relevance, quality, and latency improvements that unlock measurable business outcomes.
• Build deep diagnostic analyses by query class, price point, surface, and customer lifecycle to pinpoint where and why Search underperforms and specify concrete changes that will move key outcomes.
• Connect offline model evaluation with online and business metrics by collaborating with ML partners on evaluation design, ensuring model changes reliably improve end-user experience - not just offline scores.
• Improve data quality, instrumentation, and metric definitions for Search so that teams can reason about performance with clarity, consistency, and speed.
• Define and track leading and lagging indicators for search performance, working cross-functionally to align on benchmarks and success criteria.
• Collaborate with stakeholders to frame problems, scope analyses, and communicate findings in a clear, actionable manner to both technical and non-technical audiences.
• Leverage causal inference and robust experimental methods to assess the impact of changes and inform high-impact decisions.
• Champion best practices in data governance, reproducibility, and documentation to enable scalable and maintainable analytics workflows.
• Work closely with engineers to ensure data pipelines and feature stores support timely, reliable analysis and experimentation.
• Support the development and refinement of dashboards and reporting tools that empower teams to monitor search health and iterate quickly.
• Partner with researchers to translate model evaluation results into practical search improvements that enhance relevance and user trust.
• Identify opportunities to automate analyses and streamline insights through tooling and reusable workflows.

Requirements

• 5+ years of experience in data science or product analytics, with a track record of impact on consumer-facing products.
• Advanced SQL proficiency, including complex joins and window functions, working with large-scale datasets in modern data warehouses (e.g., Snowflake, BigQuery, Redshift).
• Proficiency in Python or R for analysis, experimentation, and modeling.
• Hands-on experience designing and analyzing A/B tests and experiments to evaluate search changes.
• Strong understanding of search and ranking concepts, including relevance, recall, precision, and latency constraints.
• Experience working with product and engineering teams to define metrics, monitor performance, and drive data-informed decisions.
• Ability to communicate complex analytical concepts clearly to non-technical stakeholders and influence without direct authority.
• Proven ability to manage multiple priorities in a fast-paced, ambiguous environment while maintaining rigorous analytical standards.

Nice to have

• Experience with search and recommendation systems in e-commerce or retail environments.
• Familiarity with modern relevance evaluation frameworks and offline/online experimentation best practices.
• Knowledge of search architecture and how model changes affect user behavior and system performance.
• Experience with data visualization tools and dashboarding platforms to surface search insights.
• Background in natural language processing or information retrieval relevant to query understanding and result ranking.

Practical notes

This is a full-time position based in the United States with remote work options. There may be requirements for occasional in-person collaboration and team events. Applicants must meet the minimum qualifications listed in the requirements section. The company reserves the right to adjust roles and responsibilities to align with business needs.