Research Scientist – Avatar Animation

HoYoverse; Mountain View (CA); On-site; USD 250,000 - 450,000; Full time

Benefits offered by this job

Healthcare premiums

Paid time off

401K plan

Life insurance

Disability insurance

Team-building

Flexible hours

Job summary

HoYoverse is seeking a research scientist to advance 3D character animation and generative models for game development, focusing on video diffusion and optimization for production use.

You will own research roadmaps, collaborate with engineers to deploy production-ready features, and work with a team pushing the boundaries of immersive worlds. A PhD or 5+ years of high-level research is required, with strong 3D and CUDA experience. Mountain View, CA-based role.

Qualifications

• PhD or 5+ years of equivalent high-level research experience.
• Strong background in 3D character animation, 3D generative models, or video diffusion models.
• Hands-on experience in video or 3D representative learning, generative model training, 3D character animation.
• Familiarity with RL, diffusion distillation, infra optimization for model training and inference, CUDA programming.
• Strong problem-solving skills and ability to work in a collaborative team.
• Publications or contributions to video generative models and 3D avatars.

Responsibilities

• Conduct original research and develop efficient generative models for high-quality character motions and facial expressions for offline and online use.
• Own research project roadmaps, collaborate with engineers to iterate on feature requirements and manage deployment risk.
• Explore asset processing techniques to ensure high-quality, optimized assets for the game development cycle.
• Stay up to date with advancements in image/video generative models and 3D animation to improve the gaming experience.

Skills

3D character animation

3D generative models

Video diffusion models

Reinforcement learning

Diffusion model distillation

CUDA programming

Education

PhD or 5+ years research

Tools

CUDA

Job description

HoYoverse is committed to providing immersive virtual world experiences to players around the world. We have brought fans popular games including Genshin Impact, Honkai: Star Rail, Honkai Impact 3rd, Tears of Themis, and Zenless Zone Zero, as well as a wide range of entertainment content.
Community is at the heart of everything we do. We are devoted to engaging fans and fostering an enthusiastic and inclusive global community.
Pushing the boundaries of imagination, we consistently explore cutting-edge game development technologies.
In the future, we will continue to expand our content production, technology research, and publishing duties through operations in offices in Singapore, Montreal, Los Angeles, Tokyo, Seoul, and other areas.
When you apply to a position with HoYoverse, we will process your personal data. To learn more, please review our comprehensive Global Applicant and Candidate Privacy Policy.

What You Will Do

• Conduct original research and develop efficient generative models for creating high quality character motions and facial expressions for both offline content creation and online gameplay.
• Take ownership of research project roadmaps, collaborating with engineers to iterate on feature requirements and managing risk for production deployment and maintenance.
• Explore and implement advanced techniques in asset processing to ensure high-quality and optimized assets for the game development cycle.
• Stay up to date with the latest advancements in image/video generative models, character animation, generative model optimization, and applying these technologies to improve the overall gaming experience.

What We Are Looking For

• PhD degree in Computer Science, or a related field, or 5+ years of equivalent high-level research experience.
• Strong background in 3D character animation, 3D generative models, or video diffusion models
• Hands-on experience on video or 3D representative learning, generative model training, 3D character animation.
• Solid knowledge or experience on following topics are preferred: RL, diffusion model distillation, infra optimization for model training and inference, CUDA programming.
• Strong problem-solving skills and the ability to work effectively in a collaborative team environment.
• Record of publications or contributions to the video generative models, character animation, 3D avatar.

Benefits

The base pay range for this position is $250,000 to $450,000 USD per year. Actual pay is based on location and may vary depending on relevant knowledge, skills, and experience from the candidate. Total compensation may include salary, company bonuses, sign-on bonuses, relocation package, and other benefits such as:

• 100% employer-paid healthcare premiums for you and your dependents
• Generous paid time off
• 401K / RRSP plan
• Employer-paid life and disability insurance
• Team-building activities throughout the year
• Flexible working hours

We are an equal opportunity employer that believes diverse backgrounds are key to bringing our concepts to life. If you're looking to play a key role in creating the best immersive virtual world experience for our users, we invite you to join our team.

We are an equal opportunity employer that believes diverse backgrounds are key to bringing our concepts to life. If you're looking to play a key role in creating the best immersive virtual world experience for our users, we invite you to join our team.