Staff Software Engineer, Machine Learning

DoorDash•San Francisco, NY

8d•Hybrid

About The Position

DoorDash is seeking a Staff Software Engineer, Machine Learning to build and maintain large-scale machine learning systems that support its delivery marketplace and advertising business. The role focuses on conceptualizing, designing, implementing, and validating algorithmic improvements, including machine learning solutions and data products that improve advertising efficiency and quality, support automated bidding and budget pacing, and help target relevant audiences. The engineer will own the end-to-end machine learning lifecycle, from ideation and offline training through online shadowing and deployment, experimentation, and post-launch measurement. They will also build and extend data and machine learning infrastructure, and scale systems and services as the business grows. The position is hybrid, with some in-office time expected, and reports to an Engineering Manager.

Requirements

M.S. or Ph.D. in a technical field such as computer science, mathematics, statistics, or physics, or equivalent.
At least 8 years of machine learning industry experience and a solid understanding of machine learning algorithms and fundamentals.
Proficiency using AI coding tools such as Claude Code, Codex, or Cursor throughout the software development lifecycle, including designing, generating code, testing, monitoring, and releasing software.
Experience building data and feature engineering pipelines at scale using PySpark and Snowflake SQL.
Experience building production machine learning systems using frameworks such as PyTorch, Keras, LightGBM, scikit-learn, or Spark ML, or related frameworks.

Responsibilities

Develop advanced machine learning models to improve advertising efficiency and quality.
Design and build optimization algorithms for budget pacing and automated bidding to achieve advertising goals.
Establish a data-driven framework to understand how bid density and market competitiveness affect advertising value and platform revenue.
Develop data solutions, such as embeddings and consumer profiles, to target relevant audiences.
Manage the end-to-end machine learning lifecycle, including ideation, offline model training, online shadowing and deployment, experimentation, and post-launch monitoring and measurement.
Build and extend data and machine learning infrastructure for advertising data applications, including data analysis, machine learning modeling, and experimentation.
Scale systems and services to support business growth.