Software Engineer (ML)

About The CompanyDoorDash is a leading technology and logistics company committed to empowering local economies by providing innovative delivery solutions. Since its inception, the company has revolutionized how consumers access goods and services, starting with food delivery and expanding into a comprehensive platform that facilitates the delivery of groceries, convenience items, and other goods. With a focus on reliability, efficiency, and customer satisfaction, DoorDash leverages cutting-edge technology to connect consumers, merchants, and delivery partners seamlessly. The company fosters a dynamic and inclusive work environment, encouraging innovation and growth among its diverse team members. DoorDash’s mission is to enable local businesses to thrive and to deliver exceptional experiences to its users through continuous technological advancements and a customer-centric approach.About The RoleWe are seeking a highly skilled Staff Software Engineer to join our Machine Learning Serving Platform team. In this pivotal role, you will be responsible for designing, developing, and optimizing systems that support real-time ML inference at scale. Your expertise will drive the next generation of our inference platform, ensuring it can handle complex models with low latency, high throughput, and cost efficiency. You will collaborate closely with cross-functional teams, including core infrastructure, applied ML, and vendor partners, to build scalable, reliable, and maintainable serving systems. This role offers an exciting opportunity to influence the technical roadmap, contribute to open-source ecosystems, and lead efforts that impact multiple business units such as Ads, Fraud detection, Logistics, and Search. The ideal candidate will combine deep technical knowledge with strong leadership skills to elevate our ML serving capabilities and support the company’s growth and innovation objectives.Qualifications8+ years of engineering experience in building or operating large-scale ML serving systemsDeep familiarity with ML inference, serving ecosystems, and deployment frameworksProficiency in leveraging and extending open-source frameworks such as NVIDIA Triton, TensorRT, ONNX Runtime, or vLLMExperience with deep learning frameworks like PyTorch and TensorFlowHands-on experience with Kubernetes, microservice architectures, and large-scale orchestration for inference workloadsCloud platform experience (AWS, GCP, Azure) focusing on scaling, observability, and cost optimizationStrong understanding of hardware acceleration (GPU, TPU, CPU) and heterogeneous hardware managementExcellent collaboration, mentorship, and communication skillsAbility to make pragmatic decisions balancing performance, reliability, and costResponsibilitiesDesign and develop scalable ML inference serving systems capable of handling complex models at low latencyOperationalize inference optimizations such as caching, batching, attention mechanisms, and quantization to improve performance and cost-efficiencyCreate abstractions and primitives that enable broad application of serving improvements across multiple workloadsLeverage and contribute to open-source serving ecosystems, integrating vendor solutions and developing custom extensions as neededImplement autoscaling, scheduling, and resource management strategies across heterogeneous hardware platformsEnsure system reliability, observability, and security through robust monitoring, alerting, and best practicesCollaborate with ML engineers, infrastructure teams, external vendors, and open-source communities to evolve the serving stackEstablish metrics, processes, and best practices to improve developer velocity, system stability, and maintainabilityMentor junior engineers and lead technical discussions to foster a high-performance engineering cultureBenefitsCompetitive salary with performance-based incentivesComprehensive health, dental, and vision insurance plans401(k) plan with employer matching contributionsPaid parental leave (up to 16 weeks)Wellness benefits and mental health support programsCommuter benefits and flexible work arrangementsPaid time off and paid sick leave in accordance with applicable lawsFamily-forming assistance and other employee support initiativesOpportunities for professional development and career growthEqual OpportunityDoorDash is an equal opportunity employer committed to fostering an inclusive and diverse workplace. We do not discriminate against any employee or applicant based on race, color, religion, national origin, gender, sexual orientation, gender identity or expression, age, disability, veteran status, or any other protected characteristic.