Reinforcement Learning Engineer

This role designs, develops, and deploys AI systems using reinforcement learning for automated game play and game balance optimization. Responsibilities include creating automated-play agents for QA and test automation, player bots, and navigation AI; applying self-play, reward design, and data analysis to game balance; and improving NPC and agent AI through behavior-model generation and adaptive AI based on player skill.

The role builds reinforcement-learning models from game-play data, including imitation learning, and constructs simulation environments for agent training. It also implements and optimizes reinforcement-learning algorithms in cloud and distributed-processing environments. The engineer works with game designers and QA teams to establish workflows that use reinforcement learning and contributes technical articles for internal and external communication.

Required qualifications include knowledge of reinforcement-learning and machine-learning theory and implementation, development experience with Python and C++, C#, or similar programming languages, experience using deep-learning frameworks such as TensorFlow, PyTorch, or JAX, and experience developing models with reinforcement-learning libraries such as Ray RLlib, Stable Baselines, or OpenAI Gym. Basic knowledge of mathematics and statistics, including linear algebra, probability and statistics, and optimization methods, is also required.

Preferred experience includes game AI development; practical projects involving automated game play or balance adjustment with reinforcement learning; distributed learning or development in AWS, GCP, Azure, or Kubernetes environments; MLOps or DevOps, including model deployment, continuous learning, and CI/CD; imitation learning and data-driven AI using game-player behavior data; simulation-environment construction; and integration of AI tools into game-development workflows. English technical-document reading and communication ability is also listed as a preferred qualification.

The position is full-time. The stated working hours are 10:00 to 19:00, including eight hours of scheduled work and a 60-minute break from 13:00 to 14:00. Average monthly overtime was approximately 18.5 hours in 2025. Work locations are offices in Shibuya and Meguro, Tokyo. Compensation is listed as JPY 4.5 million to JPY 12 million per year, with a semiannual performance incentive; the annual salary includes scheduled overtime and late-night work allowances. Benefits for regular employees include health, employment, workers’ accident compensation, and employees’ pension insurance, housing and moving allowances, child allowance, a defined-contribution pension plan, training and mentoring programs, lunch support, and other health and workplace support programs.副業は禁止されています。