Ads AI Analytics Lead II

Overview

Instacart’s Commercial Scaled Intelligence (CSI) team is an AI-first group focused on turning data into action—building products that drive revenue growth, operational efficiency, and better outcomes for our customers, shoppers, retailers, brands, and partners.

As the Ads AI Analytics Lead, you will own the intelligence behind our Ads agents. You’ll design the semantic and context layer for advertising, and build production-grade agents that analyze campaigns, diagnose performance, and recommend actions that improve ROAS, pacing, and partner outcomes. You will collaborate closely with Ads GTM, Product, Data Science, and Engineering to ship vertical agents with measurable lift.

This seat is uniquely high-impact: the tools you build are used daily by Sales, Brand Partnerships, and Ads teams, including a sales tool used by approximately 265 sellers. You will see your work show up in real workflows and on the Ads P&L. AI is the default on this team, not the experiment—and you’ll own a workstream end to end, from data models and pipelines to agent logic and the user interface. If you thrive in fast-paced environments, enjoy partnering cross-functionally, and want meaningful ownership, you’ll feel at home here.

This role is remote-friendly. Preference for candidates who can collaborate with teams based in New York City.

About the Job

• Define Ads ontologies and canonical metrics across campaigns, budgets, bids, creatives, audiences, and placements to power consistent reasoning and recommendations.
• Build robust dbt models and curated marts in Snowflake (or BigQuery) with clear data contracts, tests, SLOs, and monitoring; orchestrate pipelines with Airflow.
• Ingest, structure, and enrich unstructured Ads content; publish retrieval-ready datasets leveraging managed search/vector services to enable high-quality grounding.
• Design and evaluate RAG workflows (hybrid search, re-ranking) with explicit quality and latency targets; iterate via offline/online experiments to improve performance.
• Design agent reasoning, tools, and policies for Ads use cases, including human-in-the-loop approvals and guardrails that balance safety, cost, and speed.
• Establish evaluation suites and dashboards tracking precision/recall, calibration, hallucination rate, latency, and cost; drive continuous model and system improvements.
• Run A/B and uplift experiments to quantify business impact; own KPIs such as ROAS lift, pacing accuracy, RCA precision/recall, forecast MAPE, and time-to-insight.
• Partner with Ads Product, Ads Engineering, Sales leadership, Data Engineering, and R&D to align roadmaps, de-risk launches, and ship high-quality production agents.
• Own your workstream end to end—from data and pipelines to the UI and agent logic—delivering secure, observable, and reliable tooling that’s adopted by the field.

About You

Minimum Qualifications

• 4–7 years of experience in analytics engineering, data science, or applied AI, with advanced proficiency in Python and SQL.
• 2+ years working with ads, retail, or e‑commerce data.
• Hands-on experience with dbt and Snowflake or BigQuery, including data modeling, testing, documentation, and managing data contracts.
• Experience orchestrating data pipelines with Airflow (or a similar scheduler), including alerting and on-call support for data SLOs.
• Ability to design and run offline/online evaluations and A/B or uplift tests; familiarity with experiment design and statistical inference.
• Fluency in Ads analytics concepts: ROAS, CPA, CTR, CVR, LTV, pacing, auction dynamics, and incrementality.
• Shipped at least one production data or AI system used by business stakeholders, with demonstrable business impact.
• Experience with evaluation and guardrail frameworks and human‑in‑the‑loop QA workflows.
• Proficiency with at least one BI/visualization tool (e.g., Looker, Tableau, Mode, or Power BI).
• Bachelor’s degree in a quantitative field (e.g., Computer Science, Engineering, Statistics) or equivalent practical experience.

Preferred Qualifications

• Experience building AI-driven products or agents end to end, including retrieval design (hybrid search, re-ranking) and vector search.
• Deep expertise in advertising products and operations, with a track record of driving automation that improved ROAS, pacing, or operational efficiency.
• Applied experience with Ads modeling techniques such as forecasting, anomaly detection, uplift modeling, and causal inference.
• Hands-on experience with workflow automation or internal tooling (e.g., Retool, Superblocks, Zapier, n8n, Gumloop) and/or front-end frameworks (e.g., React) to translate insights into actions.
• Familiarity with retail media and ad ecosystems (e.g., Amazon Ads, Google Ads, Meta, Shopify, DoorDash) and their measurement frameworks.

#LI-Remote