Staff Data Scientist - AI Foundations, ML Bots

Riot Gamesabout 1 year ago
Los Angeles, California, United States
Hybrid
Full-time
Junior Level (1-3 years)

Job Description

Position Overview

On AI Foundations, our mission is to unlock cutting edge player experiences through the power of ML and AI technologies. Within this space, the ML Bots team partners with teams across Riot to accelerate the development and deployment of new machine learning & AI systems. We dive into diverse, high impact projects across Riot, and help take them from ideas to fully fledged features.

As a Staff Data Scientist specializing in applied machine learning, you will lead the design and development of Game Understanding Agents. This includes deployment of in-game Game AI capabilities that enhance both the player and developer experience. You will advance methods in reinforcement learning, imitation learning, and simulation-based training for game AI, guiding engineers on the ML Bots team in building and scaling production-ready systems. By combining modern ML approaches with deep knowledge of game mechanics, you will lead the creation of autonomous agents that can play, understand, and adapt like real players, helping establish Riot's applied ML practices in game AI and accelerating their impact across multiple projects.

Key Responsibilities

  • Lead the design and implementation of ML systems using methods including reinforcement learning, imitation learning (e.g., behavior cloning, inverse reinforcement learning), on-/off-policy algorithms, policy gradient methods, behavior shaping, and hybrid systems that combine learned policies with rule-based or scripted components.
  • Lead the development and deployment of in-game Game AI capabilities, focusing on training agents that can understand game state, make decisions, and act in ways that create compelling player experiences.
  • Create reusable training and evaluation pipelines that can be applied across multiple game genres while adapting to the unique constraints of each title.
  • Develop predictive features and signals from gameplay telemetry, unstructured game data, and simulation outputs, ensuring quality, interpretability, and reliability.
  • Collaborate with game and platform engineers, along with UX teams, to ensure the operational reliability of autonomous agents operating in live player environments.
  • Mentor junior and senior-level ML engineers, elevating expertise in advanced ML methods for game AI and guiding architectural and system-level decisions.
  • Contribute to and shape shared frameworks for autonomous agent development, accelerating adoption of best practices across Riot.

Required Qualifications

  • Extensive experience (5+ years) delivering ML systems in production, including reinforcement learning, imitation learning, or simulation-based training in rich, interactive environments such as game worlds or multi-agent simulations; or a Ph.D. in a related field with 3+ years experience.
  • Experience developing predictive features and signals from gameplay telemetry, simulation data, or other complex interactive environments.
  • Strong track record in building and optimizing agent-based systems or world models for dynamic, player-facing environments.
  • Experience with relevant ML methods, including reinforcement learning and imitation learning (such as behavior cloning and inverse reinforcement learning), on-/off-policy algorithms, policy gradient methods, behavior shaping, and hybrid systems that combine learned policies with rule-based or scripted components.
  • Expertise in experiment design, model evaluation, and optimization for autonomous agents.
  • Proven ability to incorporate human considerations into AI applications, such as responsible AI practices and UX best practices.
  • Experience mentoring engineers and collaborating with cross-disciplinary teams.
  • Familiarity with integrating ML-driven agents into live game environments with game and platform engineers.
  • Understanding of MOBA game mechanics and their implications for agent design and evaluation.
  • Proficiency in Python and experience with modern ML/data science libraries and frameworks (e.g. PyTorch/TensorFlow, pandas).

Benefits & Perks

  • Open Paid Time Off policy and flexible work schedules.
  • Medical, dental, vision, and life insurance.
  • Parental leave for you, your spouse/domestic partner, and children.
  • 401K with company match.
  • Competitive Compensation including (Los Angeles Only): Base salary range between $209,900.00 - $293,400.00 USD + incentive compensation, equity, short and long-term disability, and more.
  • A collaborative culture focused on putting players first and empowering diverse perspectives.

Required Skills

Mentoring
TensorFlow
PyTorch
Simulation-based Training
Python
Reinforcement Learning
Data Science
Imitation Learning
Game AI