Senior Machine Learning Engineer, Economy

Roblox Roblox · Consumer · San Mateo, CA · Machine Learning

Senior Machine Learning Engineer on the Economy ML team at Roblox, responsible for building and iterating on deep learning models for ranking, recommendation, pricing, and content understanding across the platform's economic surfaces. This role involves owning the full ML lifecycle, from data exploration to production deployment, and designing experiments to optimize key business metrics. The engineer will also contribute to the team's technical direction and mentor other engineers.

What you'd actually do

  1. Work backwards from ambiguous product problems to design and ship end‑to‑end ML solutions for ranking, recommendation, pricing, and content understanding across Economy surfaces.
  2. Build and iterate on deep learning retrieval and ranking models that personalize item and widget ordering across the Marketplace and other shopping experiences.
  3. Develop models and policies that optimize pricing, conversion, and revenue while balancing ecosystem health, payer experience, and creator success.
  4. Own the full ML lifecycle for your projects: data exploration, feature engineering, model design, training, evaluation, and production deployment on Roblox’s ML platform.
  5. Design and run robust experiments (A/B tests and multi‑cell experiments), tying your work to core metrics such as engagement, bookings, and creator earnings.

Skills

Required

  • BS, MS, or Ph.D. in Computer Science, Machine Learning, Statistics, or a related technical field—or equivalent practical experience building ML systems.
  • 5+ years experience with one or more of the following areas: search, recommendation, personalization, pricing, or content understanding systems for a high‑scale product.
  • Comfortable taking a problem from messy data and product ambiguity through modeling, evaluation, and stable production deployment, including building and maintaining data pipelines and feature stores.
  • Hands‑on experience with deep learning for ranking/retrieval, representation learning for text and/or vision, and large‑scale training/inference on distributed infrastructure.
  • Experiment design and statistical rigor.

Nice to have

  • Mentoring other engineers on ML best practices, code quality, and experimentation.
  • Experience with vision models.
  • Experience with distributed infrastructure.

What the JD emphasized

  • high-scale product
  • ML lifecycle
  • messy data
  • product ambiguity
  • stable production deployment
  • deep learning for ranking/retrieval
  • large-scale training/inference
  • Experiment-driven
  • healthy guardrails

Other signals

  • building ML systems
  • deep learning for ranking/retrieval
  • large-scale training/inference
  • ML lifecycle
  • experiments (A/B tests)