Real-Time ML Architect — Player Personalization & Matchmaking

Riot Games; Los Angeles (CA); On-site; USD 250,000 - 350,000; Full time

Benefits offered by this job

Medical, dental, life insurance

401k with company match

Flexible work schedules

Job summary

Riot Games is seeking a Sr. Principal ML Engineer to define and drive the modeling architecture for personalization, matchmaking, and social experiences across the player ecosystem.

You will collaborate with Product Leaders, Software Engineers, and Data Engineers to deliver intelligent and fair player experiences at scale. This role focuses on real-time inference, multi-objective optimization balancing fairness and latency, and responsible AI governance across live-service environments.

Qualifications

• 15+ years in Machine Learning or Applied AI.
• 3+ years in a principal or staff-level technical leadership role.
• Proven experience in real-time, large-scale ML systems.
• Deep expertise in graph ML, reinforcement learning, and representation learning.
• Proficiency in PyTorch, TensorFlow, JAX, and modern data/serving frameworks.
• Strong understanding of A/B testing, experiment design, and player experience metrics.

Responsibilities

• Define and lead the modeling architecture powering personalization, matchmaking, and social graph recommendations.
• Build real-time inference systems for personalized content and matchmaking at scale.
• Collaborate with Data Engineers to integrate low-latency pipelines and feature stores.
• Drive adoption of contextual bandits, reinforcement learning, and graph ML.
• Lead post-launch evaluations of algorithmic impact on community health and player sentiment.

Tools

PyTorch

TensorFlow

JAX

Ray

Kafka

Flink

Redis

Job description

Riot Games is seeking a Sr. Principal ML Engineer to define and drive the modeling architecture for personalization, matchmaking, and social experiences across the player ecosystem.

You will collaborate with Product Leaders, Software Engineers, and Data Engineers to deliver intelligent and fair player experiences at scale. This role focuses on real-time inference, multi-objective optimization balancing fairness and latency, and responsible AI governance across live-service environments.