Staff Software Engineer, Ads Modeling, Personalization, and Quality

Google Google · Big Tech · Mountain View, CA +1

Staff Software Engineer at Google working on Ads Modeling, Personalization, and Quality. The role involves designing and implementing deep learning ML models to predict user interactions with ads, incorporating various input features, and improving model efficiency and reliability. The goal is to enhance ad quality and drive business growth for App Ads.

What you'd actually do

  1. Design new deep learning based ML models to predict users’ interaction with different ad formats across Google’s various ad delivery channels.
  2. Incorporate and engineer input features from ad creatives, publisher pages/content, as well as users’ personalized ad history to improve models’ accuracy.
  3. Improve the efficiency and reliability of ML models by designing novel model architectures and adopting development and release processes.
  4. Debug and troubleshoot advertiser performance problems.
  5. Work with Product Management, UX, and partner teams to design and deliver new ad experiences. Leverage data and metrics to help evaluate product success and drive business decisions.

Skills

Required

  • ML design
  • ML infrastructure
  • model deployment
  • model evaluation
  • data processing
  • debugging
  • fine tuning
  • ML/AI algorithms
  • deep learning
  • software development
  • software design and architecture
  • testing and launching software products

Nice to have

  • data structures and algorithms
  • technical leadership
  • cross-functional project experience
  • advertising products
  • statistical modeling
  • experimentation/analysis
  • quality or modeling engineering

What the JD emphasized

  • 5 years of experience with ML design and ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging, fine tuning).
  • 5 years of experience with ML/AI algorithms and tools, deep learning or other AI/ML modeling.

Other signals

  • design new deep learning based ML models
  • predict users’ interaction with ads
  • principled optimization techniques
  • publishers monetize their content and advertisers acquire engaged users