Machine Learning, Content and Navigation

Whatnot · Consumer · San Francisco, CA · Engineering

Machine Learning Engineer role focused on building and deploying ML models for personalized navigation, search, and recommendations on a livestream shopping platform. The role involves end-to-end ML project lifecycle, from data to production, and requires experience in applied ML fields like search and recommendations.

What you'd actually do

  1. Lead the design, development, and productionization of ML models to capture intent and content signals that powers personalized navigational experience, search, and recommendations
  2. Lead ML-based projects from end-to-end: scoping and planning, data collection and feature engineering, model training and deployment, backend implementation, and online experimentation
  3. Support product initiatives like category and brand recommendations, promote high quality and relevant livestreams and products in feed and search.
  4. Work closely with teammates and cross-functional partners to implement ML-based solutions into production at scale
  5. Drive technical excellence and establish ML best practices across the team and org.

Skills

Required

  • Python
  • SQL
  • common ML frameworks
  • 4+ years of industry experience building and deploying ML models to solve user problems at scale
  • Industry experience with a track record of applying practical methods to solve real-world problems on consumer scale data
  • Experience in applied statistical and machine learning fields e.g. search, recommendations, content understanding, natural language processing, and large language models
  • Strong communication and leadership skills
  • Excellent product instincts

Nice to have

  • generalist software development experience in high growth startups

What the JD emphasized

  • building and deploying ML models to solve user problems at scale
  • track record of applying practical methods to solve real-world problems on consumer scale data
  • applied statistical and machine learning fields e.g. search, recommendations, content understanding, natural language processing, and large language models
  • shipping products and features lightning-fast

Other signals

  • ML models for personalization
  • productionization of ML models
  • ML-based projects end-to-end
  • ML-based solutions into production at scale
  • applied statistical and machine learning fields