Resume and JobRESUME AND JOB
Tencent logo

大模型训练框架研发工程师-强化学习/精调/蒸馏方向

Tencent

Software and Technology Jobs

大模型训练框架研发工程师-强化学习/精调/蒸馏方向

full-timePosted: Nov 17, 2025

Job Description

大模型训练框架研发工程师-强化学习/精调/蒸馏方向

📋 Job Overview

The role of Large Model Training Framework R&D Engineer focuses on developing and optimizing frameworks for reinforcement learning, fine-tuning, and knowledge distillation to enhance training efficiency and usability. Responsibilities include supporting distributed training with tools like Megatron-LM and DeepSpeed, building lightweight training toolchains, exploring cutting-edge technologies, and collaborating with product teams. This position aims to integrate the latest research into practical framework features to boost product competitiveness.

📍 Location: Shanghai, China

🏢 Business Unit: CSIG

📄 Full Description

1.框架开发与优化:负责强化学习、模型精调、知识蒸馏等核心模块的设计与开发,提升框架的训练效率与易用性;
2.分布式训练支持:基于Megatron-LM、DeepSpeed等工具,优化大模型分布式训练策略(数据并行/张量并行/流水并行/专家并行等),解决显存、通信与计算瓶颈;
3.工具链构建:参与开发轻量化训练框架(如LLama-Factory、swift),支持快速模型微调、部署及多硬件平台适配;
4.前沿技术探索:跟踪学术动态(如RLHF、MoE架构、FlashMLA、EPLB、DualPipe等),将最新研究成果转化为框架功能,提升产品竞争力;
5.协作与文档:与产品团队紧密配合,提供框架级解决方案;编写技术文档与案例,赋能公有云客户。

🎯 Key Responsibilities

  • 框架开发与优化:负责强化学习、模型精调、知识蒸馏等核心模块的设计与开发,提升框架的训练效率与易用性
  • 分布式训练支持:基于Megatron-LM、DeepSpeed等工具,优化大模型分布式训练策略(数据并行/张量并行/流水并行/专家并行等),解决显存、通信与计算瓶颈
  • 工具链构建:参与开发轻量化训练框架(如LLama-Factory、swift),支持快速模型微调、部署及多硬件平台适配
  • 前沿技术探索:跟踪学术动态(如RLHF、MoE架构、FlashMLA、EPLB、DualPipe等),将最新研究成果转化为框架功能,提升产品竞争力
  • 协作与文档:与产品团队紧密配合,提供框架级解决方案;编写技术文档与案例,赋能公有云客户

Locations

  • Shanghai, China

Salary

Estimated Salary Rangemedium confidence

300,000 - 800,000 CNY / yearly

Source: ai estimated

* This is an estimated range based on market data and may vary based on experience and qualifications.

Responsibilities

  • 框架开发与优化:负责强化学习、模型精调、知识蒸馏等核心模块的设计与开发,提升框架的训练效率与易用性
  • 分布式训练支持:基于Megatron-LM、DeepSpeed等工具,优化大模型分布式训练策略(数据并行/张量并行/流水并行/专家并行等),解决显存、通信与计算瓶颈
  • 工具链构建:参与开发轻量化训练框架(如LLama-Factory、swift),支持快速模型微调、部署及多硬件平台适配
  • 前沿技术探索:跟踪学术动态(如RLHF、MoE架构、FlashMLA、EPLB、DualPipe等),将最新研究成果转化为框架功能,提升产品竞争力
  • 协作与文档:与产品团队紧密配合,提供框架级解决方案;编写技术文档与案例,赋能公有云客户

Target Your Resume for "大模型训练框架研发工程师-强化学习/精调/蒸馏方向" , Tencent

Get personalized recommendations to optimize your resume specifically for 大模型训练框架研发工程师-强化学习/精调/蒸馏方向. Takes only 15 seconds!

AI-powered keyword optimization
Skills matching & gap analysis
Experience alignment suggestions

Check Your ATS Score for "大模型训练框架研发工程师-强化学习/精调/蒸馏方向" , Tencent

Find out how well your resume matches this job's requirements. Get comprehensive analysis including ATS compatibility, keyword matching, skill gaps, and personalized recommendations.

ATS compatibility check
Keyword optimization analysis
Skill matching & gap identification
Format & readability score

Tags & Categories

TencentShanghaiChinaCSIGCSIG

Answer 10 quick questions to check your fit for 大模型训练框架研发工程师-强化学习/精调/蒸馏方向 @ Tencent.

Quiz Challenge
10 Questions
~2 Minutes
Instant Score

Related Books and Jobs

No related jobs found at the moment.

Tencent logo

大模型训练框架研发工程师-强化学习/精调/蒸馏方向

Tencent

Software and Technology Jobs

大模型训练框架研发工程师-强化学习/精调/蒸馏方向

full-timePosted: Nov 17, 2025

Job Description

大模型训练框架研发工程师-强化学习/精调/蒸馏方向

📋 Job Overview

The role of Large Model Training Framework R&D Engineer focuses on developing and optimizing frameworks for reinforcement learning, fine-tuning, and knowledge distillation to enhance training efficiency and usability. Responsibilities include supporting distributed training with tools like Megatron-LM and DeepSpeed, building lightweight training toolchains, exploring cutting-edge technologies, and collaborating with product teams. This position aims to integrate the latest research into practical framework features to boost product competitiveness.

📍 Location: Shanghai, China

🏢 Business Unit: CSIG

📄 Full Description

1.框架开发与优化:负责强化学习、模型精调、知识蒸馏等核心模块的设计与开发,提升框架的训练效率与易用性;
2.分布式训练支持:基于Megatron-LM、DeepSpeed等工具,优化大模型分布式训练策略(数据并行/张量并行/流水并行/专家并行等),解决显存、通信与计算瓶颈;
3.工具链构建:参与开发轻量化训练框架(如LLama-Factory、swift),支持快速模型微调、部署及多硬件平台适配;
4.前沿技术探索:跟踪学术动态(如RLHF、MoE架构、FlashMLA、EPLB、DualPipe等),将最新研究成果转化为框架功能,提升产品竞争力;
5.协作与文档:与产品团队紧密配合,提供框架级解决方案;编写技术文档与案例,赋能公有云客户。

🎯 Key Responsibilities

  • 框架开发与优化:负责强化学习、模型精调、知识蒸馏等核心模块的设计与开发,提升框架的训练效率与易用性
  • 分布式训练支持:基于Megatron-LM、DeepSpeed等工具,优化大模型分布式训练策略(数据并行/张量并行/流水并行/专家并行等),解决显存、通信与计算瓶颈
  • 工具链构建:参与开发轻量化训练框架(如LLama-Factory、swift),支持快速模型微调、部署及多硬件平台适配
  • 前沿技术探索:跟踪学术动态(如RLHF、MoE架构、FlashMLA、EPLB、DualPipe等),将最新研究成果转化为框架功能,提升产品竞争力
  • 协作与文档:与产品团队紧密配合,提供框架级解决方案;编写技术文档与案例,赋能公有云客户

Locations

  • Shanghai, China

Salary

Estimated Salary Rangemedium confidence

300,000 - 800,000 CNY / yearly

Source: ai estimated

* This is an estimated range based on market data and may vary based on experience and qualifications.

Responsibilities

  • 框架开发与优化:负责强化学习、模型精调、知识蒸馏等核心模块的设计与开发,提升框架的训练效率与易用性
  • 分布式训练支持:基于Megatron-LM、DeepSpeed等工具,优化大模型分布式训练策略(数据并行/张量并行/流水并行/专家并行等),解决显存、通信与计算瓶颈
  • 工具链构建:参与开发轻量化训练框架(如LLama-Factory、swift),支持快速模型微调、部署及多硬件平台适配
  • 前沿技术探索:跟踪学术动态(如RLHF、MoE架构、FlashMLA、EPLB、DualPipe等),将最新研究成果转化为框架功能,提升产品竞争力
  • 协作与文档:与产品团队紧密配合,提供框架级解决方案;编写技术文档与案例,赋能公有云客户

Target Your Resume for "大模型训练框架研发工程师-强化学习/精调/蒸馏方向" , Tencent

Get personalized recommendations to optimize your resume specifically for 大模型训练框架研发工程师-强化学习/精调/蒸馏方向. Takes only 15 seconds!

AI-powered keyword optimization
Skills matching & gap analysis
Experience alignment suggestions

Check Your ATS Score for "大模型训练框架研发工程师-强化学习/精调/蒸馏方向" , Tencent

Find out how well your resume matches this job's requirements. Get comprehensive analysis including ATS compatibility, keyword matching, skill gaps, and personalized recommendations.

ATS compatibility check
Keyword optimization analysis
Skill matching & gap identification
Format & readability score

Tags & Categories

TencentShanghaiChinaCSIGCSIG

Answer 10 quick questions to check your fit for 大模型训练框架研发工程师-强化学习/精调/蒸馏方向 @ Tencent.

Quiz Challenge
10 Questions
~2 Minutes
Instant Score

Related Books and Jobs

No related jobs found at the moment.