Senior Software Engineer, Machine Learning Platform - Serving (US)
DoorDash USA · San Francisco, CA; Sunnyvale, CA; Seattle, WA
About this role
## Senior Software Engineer, Machine Learning Platform - Serving (US) ### About the Team DoorDash’s ML Serving Platform delivers **tens of millions of predictions per second**, powering search, recommendations, advertising, delivery estimates, and logistics across DoorDash, Wolt, and Deliveroo. Our customers are modelers and engineering teams across DoorDash’s internal business verticals. We build **self-serve infrastructure** that helps them bring new models into production, adopt open source software and models, and scale what they can accomplish with machine learning. ### About the Role Help build the next generation of DoorDash’s ML serving platform—connecting **request routing** and **online feature retrieval** with **model inference** on CPU and GPU infrastructure. You’ll tackle infrastructure challenges around **latency, reliability, resource efficiency, and scale**, and make those capabilities accessible through **self-serve tools and workflows**. You’ll work with experienced platform engineers and own projects end-to-end: **technical design → implementation → testing → rollout → production support**. You’ll partner with internal teams to understand modeling requirements, remove adoption barriers, and translate open source advances into measurable production improvements. ### You’ll be excited because you will… - **Empower modelers through self-serve infrastructure**: Build tools, APIs, and workflows so internal teams can deploy, configure, validate, and operate models independently. - **Bring open source innovation into production**: Evaluate and integrate inference frameworks and enable open source models—delivering reliable, efficient services at scale. - **Solve demanding inference infrastructure problems**: Improve systems for routing prediction requests, retrieving online features, and executing models at very high throughput. - **Evolve disaggregated serving architecture**: Build modular components so routing, feature retrieval, and model execution can scale and evolve independently. - **Improve Kubernetes deployment and autoscaling**: Meet latency/availability requirements while using CPU/GPU resources efficiently. - **Make adoption and rollout easier**: Build integrations, validation, and migration tooling to help teams adopt new serving capabilities with confidence. - **Own performance and reliability in production**: Use benchmarking, profiling, metrics, and tracing; participate in on-call; improve automation and runbooks. ### We’re excited about you because you… - Have **2+ years** of software engineering experience building and maintaining production services or infrastructure. - Have strong CS fundamentals and proficiency in a backend/systems language such as **Java, Kotlin, Go, C++, or Python**. - Understand distributed systems fundamentals (concurrency, networking, timeouts, failure handling, performance trade-offs). - Can independently take a defined problem through **technical design, tested implementation, and safe production rollout**. - Can debug production systems and use operational data to improve reliability, performance, or cost. - Care about the engineers using your platform and collaborate effectively with customers/partners. - Have a **CS degree (or related field)** or equivalent practical experience. ### Nice to Have - Experience with **ML inference infrastructure**, online feature retrieval, or other latency-sensitive distributed services. - Experience operating containerized workloads on *
Listing freshness
CronJobs last confirmed this listing 1d ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.