Staff Machine Learning Engineer

About the role

You will own the design and delivery of applied machine learning systems that materially improve the player experience across League of Legends. You will set the technical direction for ML within the League domain and establish reusable patterns that elevate the work of other teams beyond your immediate scope. Your responsibilities include building models, recommenders, ranking systems, and decision logic that help players discover the right champions, builds, modes, content, and return paths based on their needs and context. You will develop ML approaches that enhance in-game systems and matchmaking while balancing player experience, fairness, reliability, and operational constraints. You will translate gameplay, behavioral, and product telemetry into reliable signals and robust evaluation frameworks to guide decision making. This role requires you to partner closely with product managers, designers, analysts, and engineers to shape ambiguous opportunities into clear technical plans and shipped player-facing features. You will operate independently across multiple partner groups, driving multi-month initiatives with limited day-to-day oversight while contributing to the ML engineering community at Riot through peer reviews, documentation, and shared learnings.

Key facts

What you'll do

Define and deliver end-to-end ML solutions for player-facing problems spanning personalization, game systems, and matchmaking from problem framing through production launch and ongoing iteration.

Set technical direction for a League ML domain and create reusable modeling, evaluation, and operating patterns that raise the bar beyond your immediate team.

Build models, recommenders, ranking systems, and decision logic that help players discover the right champions, builds, modes, content, and return paths based on their needs and context.

Develop ML approaches that improve in-game systems and matchmaking quality, balancing player experience, fairness, reliability, and operational constraints.

Partner closely with product managers, designers, analysts, and engineers to shape ambiguous opportunities into clear technical plans and shipped player-facing features.

Translate gameplay, behavioral, and product telemetry into reliable signals and evaluation frameworks that inform product and design decisions.

Design and run experiments to evaluate model quality, player impact, and system tradeoffs under real-world conditions.

Work directly with game and service engineers to integrate models into League systems and services, including defining instrumentation and telemetry requirements when needed.

Operate independently across multiple partner groups, driving multi-month work with minimal day-to-day oversight while maintaining accountability for outcomes.

Contribute to the ML engineering community at Riot by participating in peer reviews, documentation, craft standards, and sharing knowledge across teams.

Help establish robust monitoring, observability, and support practices for live ML systems as they scale and evolve in production.

Champion data-driven decision making by framing complex product questions into testable hypotheses and measurable success criteria.

Explore and prototype novel modeling techniques where off-the-shelf solutions do not adequately address player needs or game dynamics.

Ensure that solutions are technically sound, maintainable, and aligned with long-term product and engineering roadmaps.

Requirements

Bachelor's degree or higher in Computer Science, Machine Learning, Statistics, or a related quantitative field, or equivalent practical experience.

6+ years of experience delivering ML systems in production, including 3+ years in applied modeling or ML research roles.

Evidence that your modeling choices have been adopted beyond your immediate team through reusable patterns, shared architectures, or influence on how others approach problems.

History of working with complex or unconventional data sources where off-the-shelf feature engineering does not apply.

Experience in production environments with interacting models, feedback loops, or systems where model behavior has downstream consequences beyond a single prediction.

Comfort with ambiguity, demonstrated by shipping in situations where the success metric, the right approach, or both were unclear at the start.

Track record of mentoring engineers across roles and levels, with evidence of raising the bar for people around you.

Excellent written and verbal communication to articulate technical concepts to both technical and non-technical stakeholders.

Background in reinforcement learning, imitation learning, generative models, or simulation-based training in interactive environments is a plus.

Experience bridging research and production by translating papers or prototypes into reliable shipped systems is a plus.

Familiarity with ML platform components such as model serving, feature stores, and ML observability is a plus.

Passion for player experience, games, or creative technology is essential for success in this role.

Nice to have

Expe