Principal Machine Learning Engineer, Ads & Promos Delivery

DoorDash DoorDash · Consumer · Sunnyvale, CA · 347 Ads Engineering

DoorDash is seeking a Principal Machine Learning Engineer to lead the technical direction for AI-first experiences in their Ads & Promos Delivery team. This role involves designing and building next-generation ranking systems using deep learning, LLMs, and sequence modeling, focusing on query understanding, representation learning, and multi-objective optimization. The engineer will own the full ML lifecycle from research to production, ensuring systems operate under strict latency, scale, and reliability constraints, and will contribute to defining how AI reshapes ads relevance in a global marketplace.

What you'd actually do

  1. Apply state-of-the-art machine learning and LLM techniques to problems across personalization, query understanding, user and content understanding.
  2. Rigorously evaluate ML and LLM models using a combination of offline analysis and online experimentation, designing metrics and experiments that clearly measure quality, impact, and tradeoffs.
  3. Own the full model lifecycle from research to production, including data analysis, model development, evaluation, offline and online A/B testing, and continuous iteration.
  4. Partner closely with product managers, data scientists, and designers to ensure AI-driven systems deliver meaningful, user-facing improvements.
  5. Stay at the forefront of ML and AI innovation by assessing emerging research and translating promising approaches into scalable, production-ready systems.

Skills

Required

  • Python
  • Java
  • C++
  • PyTorch
  • TensorFlow
  • XGBoost
  • deep learning
  • large language models
  • information retrieval
  • ranking and relevance
  • recommendation systems
  • natural language processing
  • content understanding
  • ML lifecycle management
  • offline and online evaluation
  • A/B testing

Nice to have

  • LLM-based systems
  • prompt engineering
  • retrieval-augmented generation (RAG)
  • Generative RecSys
  • user modeling
  • retrieval
  • ranking
  • relevance
  • open-source projects
  • publications
  • applied research

What the JD emphasized

  • 5+ years of experience building, deploying, and scaling ML and AI models for large-scale, user-facing or data-intensive products.
  • Deep expertise in one or more of the following areas: deep learning, large language models, information retrieval, ranking and relevance, recommendation systems, natural language processing, or content understanding.
  • Extensive experience across the full ML lifecycle, including data analysis, feature engineering, iterative model development, rigorous offline and online evaluation, and ongoing monitoring and improvement.

Other signals

  • ranking systems
  • LLMs
  • personalization
  • large-scale ML