Staff Software Engineer, ML Platform - Game Tech Group

Riot Games • Los Angeles, CA

10h

About The Position

Riot Engineers bring deep knowledge of specific technical areas but also value the chance to work in many broader domains. As a Staff Software Engineer, you’ll also dive into projects that focus on team cohesiveness and cross-team goals. You’ll lead without authority and provide other engineers with a clear illustration of extraordinary engineering. In this role, you will be enabling productionized machine learning across all of Riot, at a global scale. You’ll be applying modern MLOps practices: streamlining deployment, simplifying operations, and creating reliable infrastructure that empowers data scientists, ML engineers, and product teams to deliver value quickly and confidently.
As a Staff Software Engineer, you’ll design and implement methods for model deployment, monitoring, and lifecycle management. You’ll work on enabling all kinds of AI/ML by creating critical infrastructure; think model orchestration, feature stores, vector DBs, and everything in between. Your contributions will make ML & AI easier to adopt and operate across Riot, helping game and platform teams deliver high-impact machine learning solutions more efficiently. You will report to the Engineering Manager with Riot's Game Technology Group.

Requirements

• 6+ years of experience in software engineering, with time spent on ML/AI, platform or infrastructure teams
• Experience maintaining cloud-agnostic inference platforms (e.g. KServe) or running open source frameworks (Feast, Milvus, etc.) in a production environment
• Experience with one or more inference serving frameworks (e.g., NVIDIA Triton, TorchServe, BentoML, Seldon Core etc)
• Familiarity with GPU orchestration, performance tuning, and cost-aware scheduling
• Exposure to CI/CD workflows, infrastructure-as-code (e.g., Terraform), and artifact management
• Maintained or led development of services within a service-oriented architecture

Nice To Haves

• Proficiency in Python and experience with package management tools (e.g., Conda, Poetry)
• Exposure to AB testing and experimentation frameworks, especially in online model evaluation
• Familiarity with machine learning workflows (e.g., training, validation, deployment, monitoring) and experience working with data scientists
• Passion for player experience, game systems, or creative technology development

Responsibilities

• Implement and support ML inference infrastructure for real-time and batch serving, including deployment pipelines and CPU/GPU-aware orchestration
• Contribute to CI/CD workflows for ML artifacts, helping enable rapid iteration and safe promotion from development to production
• Implement platform observability features such as monitoring, drift detection, resource utilization, and latency tracking
• Support ML deployment best practices, including multi-version models, blue/green rollouts, shadow deployments, and safe rollback strategies
• Be thoughtful on developer UX and incorporate an iterative approach to improving
• Help lead long-term platform architecture, providing input into design decisions and contributing to team discussions
• Contribute upstream to shared infra initiatives and build feedback loops and collaboration models with other Riot platform teams
• Collaborate with researchers and game teams to understand product needs and build generalizable, reusable solutions

Benefits

• Riot focuses on work/life balance, shown by our open paid time off policy and other perks such as flexible work schedules.
• We offer medical, dental, and life insurance, parental leave for you, your spouse/domestic partner, and children, and a 401k with company match.
• Check out our benefits pages for more information.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed
• Number of Employees: 1-10 employees