[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 · Beijing

# 微信-AI Infra工程师-大模型训练与RL方向

Beijing 

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=2037411500376879104)

[OpenNash Jobs](https://jobs.opennash.com/) / [Tencent Holdings](https://jobs.opennash.com/companies/tencent-holdings/) / 微信-AI Infra工程师-大模型训练与RL方向

## Job description

### 核心训练框架开发与优化
- 负责大模型分布式训练框架（基于Megatron-LM / DeepSpeed等）的底层架构设计与核心代码开发。支撑千亿/万亿模型的高效、稳定训练；

### RL Infra 系统建设与协同优化
- 负责强化学习（PPO/GRPO/DPO等）训练框架的开发和优化。深度解决 Actor 生成（结合 vLLM/SGlang 等推理引擎）与 Critic/Reward 训练阶段的资源调度、状态流转及通信瓶颈，实现 Training 与 Inference 的极致协同；

### 算法与系统协同设计 (Co-design)
- 与前沿算法团队紧密合作，追踪并引入业界最新开源生态（如 Verl, Slime, ROLL, AReal 等），快速完成技术原型验证，加速前沿大模型对齐算法在微信海量业务场景的规模化落地。 Requirements
- 计算机相关专业，具备较强的动手能力；熟悉 Python ，具备扎实的系统编程功底和优秀的复杂系统 Debug 能力；

### 训练框架经验
- 深入理解大模型分布式训练原理，具备 Megatron-LM、DeepSpeed 或 PyTorch FSDP 等主流框架的实际源码级开发与定制经验；

### RL 与 RL Infra 储备
- 熟悉大模型后训练与对齐技术（PPO、GRPO、DPO等），熟悉 Verl、ROLL，AReal 等强化学习/分布式计算框架，可以理解并解决 RL过程中的工程痛点；

### 综合素质
- 具备极强的技术好奇心与自驱力，面对业界无先例的技术难题，能独立思考并推动解决。

## At a glance
- Posted by the employer: Not stated
- First seen by OpenNash: Jul 19, 2026
- Last checked: Oct 19, 2026
- Listed for: 92 days
- Location: Beijing[Apply on Tencent Holdings’s careers site →](https://careers.tencent.com/en-us/jobdesc.html?postId=2037411500376879104)

## More jobs at Tencent Holdings

### [3D动作游戏《狩》-后台开发-UE5 DS后台开发](https://jobs.opennash.com/companies/tencent-holdings/jobs/6d535d770b7d94786b5e/)

Beijing

### [AI infra研发工程师(北京/深圳)](https://jobs.opennash.com/companies/tencent-holdings/jobs/eda44bea14836b2b9952/)

Beijing

### [AI ⽹络集合通信库运营⼯程师](https://jobs.opennash.com/companies/tencent-holdings/jobs/59f91606e7bdc470bf0b/)

Beijing

### [Aigc内容检测算法工程师（图像与视频方向）](https://jobs.opennash.com/companies/tencent-holdings/jobs/ca1cf721bb29a8df9bdf/)

Beijing

### [AI智能体评测高级工程师](https://jobs.opennash.com/companies/tencent-holdings/jobs/9312d7b2c30640f3f245/)

Beijing

## Similar jobs at other companies

### [AI Data Infra工程师-【算法引擎部】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/13a15af01993fb02608e/)

Kuaishou Technology · Beijing

### [Agent Infra工程师（2027届）](https://jobs.opennash.com/companies/gf-securities/jobs/22731ae986d28d34bf6d/)

GF Securities · 广州市

### [AI Infra工程师](https://jobs.opennash.com/companies/xiaomi/jobs/6db9b5617cd643159aaa/)

Xiaomi · 北京 / 上海

### [AI Infra工程师-实习](https://jobs.opennash.com/companies/xiaomi/jobs/1276e7f9f442697bea08/)

Xiaomi · 上海

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/)