Staff Applied AI/ML Scientist - Central Technology, Anti-Cheat

Los Angeles · 2+ years experience · Posted Oct 12, 2026

At a glance

As a Staff Applied AI/ML Scientist on Anti-Cheat, you will lead modeling strategy across the team's portfolio of competitive integrity products.
This includes establishing architecture, setting standards, and ultimately building the weaponry that enables Riot to stay one step ahead of cheaters and botters.
The work will be high-complexity, with tangible antagonists seeking to iteratively understand the boundaries of any classifiers, almost as quick as they are deployed.

Use all of Anti-Cheat’s resources to help design, build, and maintain AI/ML pipelines from end-to-end, creating an iterative, ever-evolving series of classifiers, capable of adapting in perpetuity as attackers learn from its actions.
Innovate in the anomaly detection space by creating proven, trusted player outcomes from novel and even theoretical modelling approaches.
Leverage Riot’s centralized ML infrastructure where possible, upgrade it where necessary, and ensure that any realized technical capabilities can be capitalized on by other teams and products.
Independently analyze and develop prototypes for emerging challenges in the anti-cheat space, including challenges of cost efficacy.
Refine modeling and feature invention strategy across projects; improve architecture trade-offs, signal extraction techniques, and quality standards for complex data sources.
Develop mission-critical machine learning and artificial intelligence systems from scratch, including gathering requirements and designing scalable, production-ready architecture that significantly impacts the team and product.
Reduce ambiguity in complex problem spaces by leading technical discovery and prototyping efforts that have a strategic impact on the team.
Establish recruiting practices across multiple teams; serve as a trusted interviewer for related roles.
Mentor junior staff by sharing your reasoning behind design decisions and result interpretations.

Ph.D. in Machine Learning, AI, Statistics, Math, or related Computer Science/Quantitative field with 3+ years of industry experience (including Postdoc), or equivalent experience (i.e., M.S. with 4-6+ years of relevant experience, or B.S. with 6-8+ years of relevant experience).
2+ years of experience working directly in anti-cheat, anti-fraud, or anti-virus spaces.
Working knowledge of production ML systems to engage credibly on model serving, CI/CD for ML, observability, and cost tradeoffs, and write the code daily.
History of working at the boundary between research and production, where interesting problems require both scientific rigor and engineering pragmatism.
Experience establishing evaluation practices across AI/ML projects in partnership with product data scientists; guide experiment design for measuring model impact and set technical evaluation standards.
Deep understanding of traditional machine learning models, with familiarity in deep learning technologies and their applications.
History of working with complex or unconventional data sources where off-the-shelf feature engineering doesn’t apply.
Comfort representing ML capabilities in cross-disciplinary forums and translating technical tradeoffs for product, design, and leadership audiences.