QQ浏览器-大模型研发工程师
Tencent
QQ浏览器-大模型研发工程师
Job Description
QQ浏览器-大模型研发工程师
📋 Job Overview
The role of Large Model R&D Engineer at QQ Browser involves developing the full pipeline for AI search business using large models, including architecture design, data preprocessing, training, deployment, and inference acceleration. Responsibilities include designing and developing core modules of the inference framework, implementing engineering solutions for inference acceleration techniques, and researching frontier technologies to integrate advanced inference methods into business applications. This position focuses on pushing innovations in sparse, heterogeneous, and distributed inference to enhance browser AI capabilities.
📍 Location: Beijing, China
🏢 Business Unit: CSIG
📄 Full Description
2.负责推理框架核心模块的设计与开发，包括算子调度、流量调度、模型管理、推理引擎集成等工作；
3.负责推理加速方法的工程实现和落地，包括但不限于模型剪枝、模型量化、动态batch等方法；
4.调研前沿技术，推动稀疏化推理、异构推理、分布式推理等技术在业务中的集成应用。
🎯 Key Responsibilities
- Participate in the full-process development of large models for browser AI search business, including architecture design, data preprocessing, training, deployment, and inference acceleration.
- Responsible for the design and development of core modules in the inference framework, including operator scheduling, traffic scheduling, model management, and integration of inference engines.
- Responsible for the engineering implementation and deployment of inference acceleration methods, including but not limited to model pruning, model quantization, dynamic batching, etc.
- Research frontier technologies and promote the integration and application of sparse inference, heterogeneous inference, distributed inference, and other technologies in business.
Locations
- Beijing, China
Salary
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
- Participate in the full-process development of large models for browser AI search business, including architecture design, data preprocessing, training, deployment, and inference acceleration.
- Responsible for the design and development of core modules in the inference framework, including operator scheduling, traffic scheduling, model management, and integration of inference engines.
- Responsible for the engineering implementation and deployment of inference acceleration methods, including but not limited to model pruning, model quantization, dynamic batching, etc.
- Research frontier technologies and promote the integration and application of sparse inference, heterogeneous inference, distributed inference, and other technologies in business.
Tags & Categories
QQ浏览器-大模型研发工程师
Tencent
QQ浏览器-大模型研发工程师
Job Description
QQ浏览器-大模型研发工程师
📋 Job Overview
The role of Large Model R&D Engineer at QQ Browser involves developing the full pipeline for AI search business using large models, including architecture design, data preprocessing, training, deployment, and inference acceleration. Responsibilities include designing and developing core modules of the inference framework, implementing engineering solutions for inference acceleration techniques, and researching frontier technologies to integrate advanced inference methods into business applications. This position focuses on pushing innovations in sparse, heterogeneous, and distributed inference to enhance browser AI capabilities.
📍 Location: Beijing, China
🏢 Business Unit: CSIG
📄 Full Description
2.负责推理框架核心模块的设计与开发，包括算子调度、流量调度、模型管理、推理引擎集成等工作；
3.负责推理加速方法的工程实现和落地，包括但不限于模型剪枝、模型量化、动态batch等方法；
4.调研前沿技术，推动稀疏化推理、异构推理、分布式推理等技术在业务中的集成应用。
🎯 Key Responsibilities
- Participate in the full-process development of large models for browser AI search business, including architecture design, data preprocessing, training, deployment, and inference acceleration.
- Responsible for the design and development of core modules in the inference framework, including operator scheduling, traffic scheduling, model management, and integration of inference engines.
- Responsible for the engineering implementation and deployment of inference acceleration methods, including but not limited to model pruning, model quantization, dynamic batching, etc.
- Research frontier technologies and promote the integration and application of sparse inference, heterogeneous inference, distributed inference, and other technologies in business.
Locations
- Beijing, China
Salary
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
- Participate in the full-process development of large models for browser AI search business, including architecture design, data preprocessing, training, deployment, and inference acceleration.
- Responsible for the design and development of core modules in the inference framework, including operator scheduling, traffic scheduling, model management, and integration of inference engines.
- Responsible for the engineering implementation and deployment of inference acceleration methods, including but not limited to model pruning, model quantization, dynamic batching, etc.
- Research frontier technologies and promote the integration and application of sparse inference, heterogeneous inference, distributed inference, and other technologies in business.
Tags & Categories