[Skip to main content](#main-content)

[OpenNash Jobs](https://jobs.opennash.com/)
[Hiring report](/reports/hiring/) · [All Tencent Holdings jobs](https://jobs.opennash.com/companies/tencent-holdings/) · [Search jobs](/search/)

Tencent Holdings · Shenzhen

# 腾讯游戏-多模态大模型算法研究员-动作生成方向

Shenzhen 

Listed on Tencent Holdings’s official careers site. Listed as of October 19, 2026. Check that it is still open and apply there.
[Apply on Tencent Holdings’s careers site →](https://careers.tencent.com/en-us/jobdesc.html?postId=2083011858134118400)

[OpenNash Jobs](https://jobs.opennash.com/) / [Tencent Holdings](https://jobs.opennash.com/companies/tencent-holdings/) / 腾讯游戏-多模态大模型算法研究员-动作生成方向

## Job description

### Responsibilities
- 负责构建和优化面向动作生成的多模态大模型架构，探索文本、视觉信号、3D 动作序列等模态的深度融合与对齐；
- 负责研究多模态场景下，高维、连续3D动作数据的Tokenization 方法；
- 负责探索多模态动作大模型 Scaling Law，包括数据量、参数量级、计算量等，通过模型规模化提升生成能力；
- 负责探索多模态对齐大模型，支持语音、文本、动作等多模态对齐，未来进一步支持多模态实时输出；
- 负责探索任意角色动画生成，可对任意角色与骨架均能生成自然的动画；
- 负责探索、研发动捕精修大模型，可对动捕过程各类噪声自动去除，达到精修品质；
- 负责探索环境感知的交互动画生成，支持角色与物体、场景、其他角色的交互，确保生成交互动作的合理性。 Requirements
- 计算机、人工智能等相关专业硕士或博士学位，在深度学习领域有扎实的理论功底；
- 深入理解主流多模态融合架构（例如 Single-stream、Double-stream 等），能够针对不同模态特征进行灵活的 Transformer 模块设计；
- 熟悉端到端预训练、SFT、RL 微调等流程；
- 熟练使用 Python，熟练使用 PyTorch 框架；
- 具备 3D 骨骼动画或人体运动学（IK/FK, SMPL 等人体参数化模型）相关经验者优先；
- 具备人体物理仿真（如 PhysX, Isaac Gym, MuJoCo）或基于强化学习的动作控制经验者优先；
- 在 CVPR、ICCV、ECCV、SIGGRAPH 等顶会发表过高质量论文，或在相关开源项目、算法竞赛中获得优异成绩者优先；
- 具备极强的论文复现与改进能力，能够敏锐捕捉大语言模型、视频生成领域的最新技术并将其迁移至动作生成领域。

## At a glance
- Posted by the employer: Not stated
- First seen by OpenNash: Oct 12, 2026
- Last checked: Oct 19, 2026
- Listed for: 7 days
- Location: Shenzhen[Apply on Tencent Holdings’s careers site →](https://careers.tencent.com/en-us/jobdesc.html?postId=2083011858134118400)

## More jobs at Tencent Holdings

### [#QQ游戏中心-发行运营#](https://jobs.opennash.com/companies/tencent-holdings/jobs/9d1cfc780fbcdb0a0a4a/)

Shenzhen

### [3D 动作游戏《狩》美术项目经理（APM）](https://jobs.opennash.com/companies/tencent-holdings/jobs/74fb431b49d65f1be30c/)

Shenzhen

### [3D动作游戏《狩》-文案策划-角色方向](https://jobs.opennash.com/companies/tencent-holdings/jobs/aefb8e04d3a158528ea5/)

Shenzhen

### [3D动作游戏《狩》-游戏运营-PC渠道运营](https://jobs.opennash.com/companies/tencent-holdings/jobs/bd0613468de8267b860a/)

Shenzhen

### [3D动作游戏《狩》-游戏运营-内容生态运营](https://jobs.opennash.com/companies/tencent-holdings/jobs/a1394d4df104126e0aac/)

Shenzhen

## Similar jobs at other companies

### [多模态大模型算法研究员-AI安全与治理](https://jobs.opennash.com/companies/china-telecom/jobs/d8e7b24c254039e62bdf/)

China Telecom · 上海市

### [顶尖实习-多模态大模型算法研究员-MiMo](https://jobs.opennash.com/companies/xiaomi/jobs/26ae6b3f300c7d9d55e7/)

Xiaomi · 北京

### [顶尖应届-多模态大模型算法研究员-MiMo](https://jobs.opennash.com/companies/xiaomi/jobs/84829538541c5de8e436/)

Xiaomi · 北京

OpenNash lists jobs from employers’ own careers sites and does not handle applications.
Dates come from the employer where stated; “first seen” and “last checked” are our own observations.

OpenNash Jobs · Official listings with dates and links to the employer. [Weekly hiring report](/reports/hiring/) · [Methodology](/methodology/)