Software Engineer, Machine Learning - Credit & Refund Optimization

About the Team Join the team focused on building intelligent, personalized systems that drive fairness, efficiency, and trust in the DoorDash platform. We own the credits and refunds experience—key components of customer satisfaction and retention—and we’re pioneering new ways to optimize and personalize these decisions at scale using causal inference and optimization. About the Role We're seeking a Machine Learning Engineer to lead the development of state-of-the-art ML systems that personalize and optimize credits and refund decisions. This work is critical to balancing cost efficiency with long-term customer retention and experience. In this high-impact role, you will partner with cross-functional leaders to design and deploy causal models and optimization algorithms that influence millions of user experiences every week. You’re excited about this opportunity because you will… Designing and deploying causal inference models to accurately assess the impact of refunds and credits on customer satisfaction, retention, and behavior Developing optimization frameworks that balance customer experience with operational cost, under policy and budget constraints Building personalized decision systems that adapt to customer preferences and platform dynamics in real time Collaborating with engineering, product, and data science partners to shape the roadmap for trust, service recovery, and consumer experience Leading end-to-end model development, including experimentation, deployment, monitoring, and iteration We’re excited about you because you have: 3+ years of industry experience delivering machine learning systems with clear business impact, especially in personalization, optimization, or causal inference Proficiency in using AI coding tools (e.g., Claude Code, Codex, Cursor) in the full software development lifecycle, including designing, generating code, testing, monitoring and releasing software Deep expertise in statistical modeling and causal inference (e.g., uplift modeling, treatment effect estimation, synthetic controls, instrumental variables) Experience designing and deploying optimization algorithms (e.g., multi-objective optimization, bandits, constrained optimization) Proficiency in Python and ML tooling such as PyTorch, Spark, and MLflow A strong product sense and ability to translate business objectives into technical solutions M.S. or Ph.D. in a quantitative field (e.g., Computer Science, Statistics, Operations Research, Economics, Mathematics) Excellent communication skills and a track record of cross-functional leadership About the Team The Storage teams build and operate online stateful systems and abstractions that are reliable, efficient, secure and easy to use for DoorDash Engineering. The teams are responsible for understanding Product Engineering’s evolving needs and developing platform and infrastructure capabilities to serve them. The team currently supports CockroachDB, Cassandra, Kafka and Redis as well as data abstraction services to reduce the complexity of interacting with storage systems for Product Engineers. About the Role We’re hiring a Data Solutions Engineer with deep expertise in distributed databases, particularly Apache Cassandra, Redis, Kafka, and database agnostic abstractions. In this role, you will design, optimize, and scale distributed data access layers that power DoorDash’s most critical systems, ensuring high availability, low latency, and fault tolerance. You’ll serve as a hands-on architect and technical partner to product engineering and infrastructure teams, helping translate complex business requirements into resilient and scalable data models. Your work will directly influence the evolution of Taulu , DoorDash’s unified storage abstraction layer, by shaping best practices and identifying platform gaps through real world engagements. This is a high-impact, cross functional role that combines deep technical expertise with a customer centric approach. You’ll lead solutioning engagements from design through production, drive the adoption of Taulu modeling best practices, and ensure that our systems meet goals around reliability, cost efficiency, and velocity. You must be located in San Francisco, Sunnyvale, Seattle or New York for this hybrid opportunity.  You’re excited about this opportunity because you will… Design and implement highly scalable, fault tolerant distributed database solutions using Taulu, Apache Cassandra, Redis, Kafka, and other paved path storage solutions.  Architect and optimize multi-region, globally distributed systems to meet our high standards for availability, latency, and throughput. Lead data modeling, performance tuning, and capacity planning for large-scale, mission-critical storage workloads. Partner with product engineering and infrastructure teams to deeply understand domain specific data needs and guide them in adopting paved path storage solutions. Serve as the DRI for solutioning engagements , owning modeling in Taulu from experimentation through launch and scale. Shape the evolution of Taulu by identifying abstraction gaps and converting customer feedback into platform improvements. Apply workload-aware design patterns, including caching strategies, partitioning, and consistency tuning to improve performance and efficiency. Drive adoption of operational best practices across observability, schema design, capacity planning, and cost optimization across storage systems. Promote clarity and continuity by contributing to solutioning playbooks, decision logs, and architectural documentation. We’re excited about you because… You have 10+ years of experience designing and scaling distributed data systems, with deep expertise in NoSQL technologies like Apache Cassandra, DynamoDB, or ScyllaDB. You have a strong command of distributed system concepts such as replication, partitioning, tunable consistency, and failure recovery. You’ve l