Senior Software Engineer, Core Ex AI Team

Overview

About the Role

In this role as a Senior Software Engineer, you will sit at the intersection of core backend engineering and applied machine learning. This is a hybrid role for a builder who can not only write production-grade code but also actively design and train intelligent systems. You will identify opportunities to apply intelligence by training your own lightweight models and heuristics to solve immediate product needs. Beyond your own modeling work, you will partner closely with Machine Learning Engineers to operationalize their research and deploy complex models at scale. You will architect the full lifecycle from feature selection and model integration to building the services and data pipelines that run them in production. Whether you are developing a custom re-ranking algorithm or optimizing inference latency for a deep learning model, you will own the end-to-end technical execution where systems meet AI.

About the Team

You will join the Search and Personalization team, the central engine that powers discovery across the entire Instacart marketplace. We own the search experience end-to-end, from the moment a user types a query to the final ranking of results. Beyond search, we drive the personalization intelligence that underpins systems across the entire company, ensuring every customer sees the most relevant products and recommendations. We function like a high-velocity startup within a well-established organization, combining massive scale with the agility to experiment and innovate. Join us to build the adaptive, intelligent core of Instacart that transforms a simple grocery run into a personalized shopping journey

About the Job

• Design and implement backend features that incorporate ML/AI: Develop enhancements to Instacart’s systems(search, recommendations, etc.) using your own lightweight ML techniques. You will identify product needs and independently build solutions such as a re-ranking module that boosts diverse items, simple logistic regression models for personalization, or prompt engineering workflows for content generation.
• Collaborate on productionizing complex models: Work closely with Machine Learning Engineers to integrate their advanced research models (such as deep recommendation engines) into production services. You will handle the software architecture for model serving, optimize inference performance, and ensure these models run reliably and efficiently at high scale.
• Develop data-driven algorithms and heuristics: Create robust pipelines for data aggregation and rule-based heuristics to power features like "trending items" or "popular searches." You will write efficient queries or real time pipelines to compute these metrics and integrate the results into user-facing feeds.
• Implement and monitor evaluation metrics: Adopt a debug-first and analytical mindset for all intelligent features. You will design offline evaluation methods to validate your improvements before launch and develop dashboards to track performance metrics such as accuracy, latency, and drift in the production environment.
• Maintain high engineering standards: Ensure that all code meets Instacart’s quality standards. You will write unit and integration tests for both backend services and ML pipelines, conduct code reviews, and ensure the systems you build are scalable, maintainable, and easy to debug.

About You

Minimum Qualifications

• Bachelor’s or Master’s degree in Computer Science (or related field), or equivalent experience.
• 5 years of experience with software development in one or more programming languages.
• 2 years of experience with machine learning algorithms and tools, or artificial intelligence.
• Hands-on experience with fundamental ML concepts and tools. 
• Demonstrated ability to work in cross-functional teams and partnering with ML engineers, product managers, and data scientists. 
• Willingness to learn new AI technologies and adapt to the iterative, experiment-driven workflow of ML projects.
• Strong SQL skills to derive insights from data. 

Preferred Qualifications

• Experience deploying ML models into high-traffic production environments
• Experience building data pipelines (batch vs. real-time) for ML features is beneficial.
• Ability to design systems that integrate ML components, covering areas such as model deployment, feature engineering, and update strategies
• Ability to design offline experiments and analyze results. Comfortable with metrics such as precision/recall, AUC, or other evaluation techniques to judge performance without always needing an online experiment.