[2026] Senior Machine Learning Engineer, Engine Optimization - Phd Early Career

Roblox Roblox · Consumer · San Mateo, CA · Early Career

Senior Machine Learning Engineer focused on real-time engine optimization for Roblox's platform. The role involves analyzing massive-scale telemetry, designing ML models for predictive resource allocation and content delivery, building adaptive control systems, and integrating ML solutions into the core gameplay engine. The goal is to replace heuristic logic with data-driven decision-making to improve stability, visual quality, and responsiveness across billions of global play sessions.

What you'd actually do

  1. Analyze massive-scale engine performance, streaming patterns, and user behavior telemetry to uncover optimization opportunities and guide the long-term ML roadmap.
  2. Design ML models that infer player and interaction patterns for predictive resource management and content delivery.
  3. Build adaptive control systems that translate ML outputs into real-time adjustments of fidelity and system decisions, ensuring high-quality experiences without compromising stability or latency.
  4. Collaborate with core engine and performance engineering teams to integrate ML solutions directly into the critical path of gameplay across multiple platforms.
  5. Define the architectural strategy for deploying and scaling ML across resource management and streaming components at massive global scale.

Skills

Required

  • applied ML
  • reinforcement learning for control
  • predictive modeling
  • time-series analysis
  • intent inference
  • trajectory prediction
  • real-time optimization
  • C++
  • Python
  • Go
  • Java
  • systems-level concepts
  • memory management
  • threading
  • OS signals

Nice to have

  • gaming
  • simulation
  • robotics
  • mobile environments

What the JD emphasized

  • performance-critical systems
  • real-time engine optimization
  • real-time adjustments
  • real-time systems

Other signals

  • applying machine learning in real-time engine optimization
  • establish the ML framework for predictive resource allocation and content fetching
  • replacing heuristic-based logic with adaptive, data-driven decision-making
  • ML outputs into real-time adjustments of fidelity and system decisions
  • deploying and scaling ML across resource management and streaming components at massive global scale