RL Infra Engineer - Varsapura

HoYoverse•Los Angeles, CA

About The Position

HoYoverse is seeking an RL Infra Engineer to build and own the infrastructure foundation for its reinforcement learning framework. The role will enable RL-driven gameplay systems to scale across current and future UE5 projects. It is a hands-on, hybrid role between ML research and game/engine engineering, focused on turning research ideas into robust, deployable, production-ready systems that run inside real game environments. The engineer will collaborate with the gameplay team to deliver machine learning and AI solutions for Varsapura, HoYoverse’s upcoming flagship title. They will partner with gameplay engineers to prototype, optimize, and productionize reinforcement learning pipelines; own the technical roadmap for RL infrastructure; and deploy and operate learning agents in live or simulated UE-based environments while optimizing infrastructure for runtime inference.

Requirements

8+ years of professional experience in software engineering, machine learning, or related technical roles.
Strong proficiency with Python and C++.
Experience with game development workflows, including debugging, profiling, and version control.
Solid understanding of deep neural network architectures and reinforcement learning concepts.
Experience with deep-learning frameworks such as PyTorch and TensorFlow.
Experience with distributed machine learning systems on cloud infrastructure.
Experience deploying and optimizing machine learning applications in production environments.

Nice To Haves

MS or PhD in Computer Science, Mathematics, or a related technical field.
Experience with end-to-end reinforcement learning workflows, from training to production deployment.
Experience working with Unreal Engine.
Experience with cross-functional collaboration in fast-moving engineering environments.

Responsibilities

Collaborate with the gameplay team to deliver machine learning and AI solutions that enhance the game experience on Varsapura.
Partner with gameplay engineers to prototype, optimize, and productionize reinforcement learning pipelines.
Own the technical roadmap for RL infrastructure, identifying bottlenecks and driving improvements in reliability, scalability, and iteration speed.
Deploy and operate learning agents in live or simulated UE-based environments.
Optimize infrastructure for runtime inference.