Staff Machine Learning Engineer (ML Platform)

TL;DR

Staff Machine Learning Engineer (ML Platform): Designing and scaling the infrastructure powering AI and machine learning systems across game development and player experiences with an accent on model serving, orchestration, and deployment workflows. Focus on architecting systems for model deployment, observability, and lifecycle management to move ML systems from experimentation into reliable production services.

Location: United States (implied by benefits and legal requirements)

Company

Riot Games is a leading game developer focused on creating player-centric experiences and high-quality games.

What you will do

• Design and operate AI & ML inference infrastructure, including deployment pipelines and CPU/GPU-aware orchestration.
• Develop CI/CD workflows to enable rapid iteration and safe promotion from development to production.
• Optimize infrastructure supporting varied model architectures (from foundation models to gradient boosted trees) for high throughput and low latency.
• Establish ML deployment best practices, including multi-version models, blue/green rollouts, and shadow deployments.
• Influence long-term platform architecture and shape the technical direction of the ML ecosystem.
• Collaborate with researchers and game teams to build reusable platform capabilities.

Requirements

• 6+ years of engineering experience, specifically within ML/AI, platform, or infrastructure teams.
• Experience operating inference platforms such as KServe and production ML infrastructure like Feast or Milvus.
• Proficiency with inference serving frameworks including NVIDIA Triton/Dynamo or TorchServe.
• Experience with GPU orchestration, performance tuning, and cost-aware scheduling.
• Strong knowledge of CI/CD workflows, infrastructure-as-code (Terraform), and artifact management.
• Experience building and operating services within distributed or service-oriented architectures.

Nice to have

• Experience building ML infrastructure in real-time or latency-sensitive environments.
• Hands-on experience optimizing LLMs and diffusion models for throughput and reliability.
• Familiarity with agentic workflows and orchestration frameworks for LLM-based systems.
• Passion for player experience and creative technology development.

Culture & Benefits

• Open paid time off policy and flexible work schedules.
• Comprehensive medical, dental, and life insurance.
• Parental leave for employees, spouses/domestic partners, and children.
• 401k plan with company match.
• Collaborative environment focused on player empathy and experience.