Senior Technical Program Manager, Caper Machine Learning

<div class="content-intro"><p><strong>We're transforming the grocery industry</strong></p> <p><span class="im">At Instacart, we invite the world to share love through food because we believe everyone should have access to the food they love and more time to enjoy it together. Where others see a simple need for grocery delivery, we see exciting complexity and endless opportunity to serve the varied needs of our community. We work to deliver an essential service that customers rely on to get their groceries and household goods, while also offering safe and flexible earnings opportunities to Instacart Personal Shoppers.</span></p> <p>Instacart has become a lifeline for millions of people, and we’re building the team to help push our shopping cart forward. If you’re ready to do the best work of your life, come join our table.</p> <p><strong>Instacart is a Flex First team </strong></p> <p>There’s no one-size fits all approach to how we do our best work. Our employees have the flexibility to choose where they do their best work—whether it’s from home, an office, or your favorite coffee shop—while staying connected and building community through regular in-person events. <a href="https://instacart.careers/remote/" target="_blank" data-saferedirecturl="https://www.google.com/url?q=https://instacart.careers/remote/source=gmailust=1651869232122000usg=AOvVaw37OlxP8hAKN7nq4YwHQH7e">Learn more about our flexible approach to where we work.</a></p></div><h2><strong>Overview</strong></h2> <p>Caper, an Instacart team building AI-powered checkout experiences, is on the cutting edge of physical AI—bringing computer vision and on-device machine learning to the real world through smart carts and connected retail hardware.</p> <p>We are seeking a Senior Technical Program Manager to lead complex, multi-quarter machine learning computer vision engineering programs that power the heart of Caper: high-quality data pipelines, robust model training and evaluation, and reliable on-cart deployment at scale. You will partner closely with computer vision and machine learning engineers, Android engineers, hardware teams, product, operations, and the executive team to build the roadmap, drive execution, and deliver measurable improvements to model performance and in-store outcomes.</p> <p>This role is ideal for a builder who thrives in a fast-paced, evolving environment and enjoys rolling up their sleeves to turn complex, cross-functional work into predictable delivery. Remote-friendly across the US and Canada, with a preference for West Coast time zones to maximize collaboration with our partners.</p> <h2> </h2> <h2><strong>About the Job</strong></h2> <ul> <li>Own end-to-end execution of ML programs across data collection, labeling, training, evaluation, and on-device deployment—defining scope, milestones, risks, and success metrics tied to accuracy, latency, and in-store experience.</li> <li>Build and maintain cross-functional plans with computer vision/ML, Android, hardware, MLOps, data engineering, QA, and field operations; run cadences, surface tradeoffs, and drive on-time, high-quality releases.</li> <li>Lead data operations at scale, including in-store capture, synthetic generation, and third-party annotation—setting data quality bars, SLAs, and privacy standards in partnership with Legal and Security.</li> <li>Establish rigorous evaluation frameworks that connect offline metrics and on-device performance to business outcomes (e.g., recognition accuracy, shrink reduction, throughput), including pilots and A/B tests in stores.</li> <li>Drive deployment readiness and reliability: model packaging for edge devices, rollout plans, monitoring and alerting, incident response, and postmortems with clear, actionable follow-ups.</li> <li>Communicate program status and insights to stakeholders and executives; proactively manage dependencies and risks across a ~25-person cross-functional org and external vendors.</li> </ul> <p> </p> <h2><strong>About You</strong></ ... (truncated, view full listing at source)