腾讯云BI-后台开发工程师
Tencent
腾讯云BI-后台开发工程师
Job Description
腾讯云BI-后台开发工程师
📋 Job Overview
The Backend Development Engineer for Tencent Cloud BI focuses on developing an intelligent analysis platform by leading the architecture design of ChatBI, integrating large model technologies like RAG, NL2SQL, and NL2DSL for natural language-driven data querying and visualization. The role involves AI-driven product design to enhance data analysis products with LLM capabilities, creating zero-code AI experiences for SaaS and on-premises deployments. Responsibilities include implementing AI technical solutions, such as model fine-tuning and vector database integration, and tackling complex issues in intelligent scenarios to ensure performance and stability across environments.
📍 Location: Shenzhen, China
🏢 Business Unit: CSIG
📄 Full Description
1.智能分析平台研发：主导腾讯云ChatBI 的架构设计，深度融合大模型技术（如 RAG、NL2SQL、NL2DSL），实现自然语言驱动的数据查询与可视化分析能力，推动产品向 AI 原生方向升级。
2.AI 驱动产品设计：负责腾讯云数据分析类产品的智能化迭代，基于 LLM 能力重构交互逻辑（如自然语言语义解析、动态知识注入），打造 “零代码” AI 分析体验，覆盖 SaaS 与私有化部署场景。
3.AI 技术方案落地：根据业务需求输出兼具创新性与可行性的技术方案，主导大模型微调（如领域适配、参数高效优化）、向量数据库集成、智能查询优化等核心模块开发，确保代码质量与工程落地性。
4.智能场景问题攻坚：针对 SaaS 与私有化客户的复杂需求，通过 AI 技术手段（如模型推理优化、实时数据处理）解决智能分析链路中的性能瓶颈、语义歧义等问题，保障 AI 功能在不同部署环境下的稳定性与准确性。
2.AI 驱动产品设计：负责腾讯云数据分析类产品的智能化迭代，基于 LLM 能力重构交互逻辑（如自然语言语义解析、动态知识注入），打造 “零代码” AI 分析体验，覆盖 SaaS 与私有化部署场景。
3.AI 技术方案落地：根据业务需求输出兼具创新性与可行性的技术方案，主导大模型微调（如领域适配、参数高效优化）、向量数据库集成、智能查询优化等核心模块开发，确保代码质量与工程落地性。
4.智能场景问题攻坚：针对 SaaS 与私有化客户的复杂需求，通过 AI 技术手段（如模型推理优化、实时数据处理）解决智能分析链路中的性能瓶颈、语义歧义等问题，保障 AI 功能在不同部署环境下的稳定性与准确性。
🎯 Key Responsibilities
- Lead the architecture design of Tencent Cloud ChatBI, deeply integrating large model technologies (e.g., RAG, NL2SQL, NL2DSL) to enable natural language-driven data querying and visualization analysis, advancing the product towards AI-native upgrades.
- Handle AI-driven product design for Tencent Cloud data analysis products, reconstructing interaction logic based on LLM capabilities (e.g., natural language semantic parsing, dynamic knowledge injection) to create a 'zero-code' AI analysis experience covering SaaS and on-premises deployment scenarios.
- Deliver innovative and feasible AI technical solutions based on business needs, leading the development of core modules such as large model fine-tuning (e.g., domain adaptation, parameter-efficient optimization), vector database integration, and intelligent query optimization, ensuring code quality and engineering feasibility.
- Address complex demands from SaaS and on-premises customers by using AI techniques (e.g., model inference optimization, real-time data processing) to resolve performance bottlenecks, semantic ambiguities, and other issues in the intelligent analysis pipeline, guaranteeing stability and accuracy of AI functions across deployment environments.
🛠️ Required Skills
- Proficiency in large model technologies such as RAG, NL2SQL, NL2DSL
- Experience with LLM capabilities including natural language semantic parsing and dynamic knowledge injection
- Skills in large model fine-tuning, domain adaptation, and parameter-efficient optimization
- Knowledge of vector database integration and intelligent query optimization
- Expertise in model inference optimization and real-time data processing
- Strong problem-solving abilities for performance bottlenecks and semantic ambiguities in AI systems
- Backend development skills ensuring code quality and engineering feasibility in SaaS and on-premises environments
Locations
- Shenzhen, China
Salary
Estimated Salary Rangemedium confidence
180,000 - 350,000 CNY / yearly
Source: ai estimated
* This is an estimated range based on market data and may vary based on experience and qualifications.
Skills Required
- Proficiency in large model technologies such as RAG, NL2SQL, NL2DSLintermediate
- Experience with LLM capabilities including natural language semantic parsing and dynamic knowledge injectionintermediate
- Skills in large model fine-tuning, domain adaptation, and parameter-efficient optimizationintermediate
- Knowledge of vector database integration and intelligent query optimizationintermediate
- Expertise in model inference optimization and real-time data processingintermediate
- Strong problem-solving abilities for performance bottlenecks and semantic ambiguities in AI systemsintermediate
- Backend development skills ensuring code quality and engineering feasibility in SaaS and on-premises environmentsintermediate
Responsibilities
- Lead the architecture design of Tencent Cloud ChatBI, deeply integrating large model technologies (e.g., RAG, NL2SQL, NL2DSL) to enable natural language-driven data querying and visualization analysis, advancing the product towards AI-native upgrades.
- Handle AI-driven product design for Tencent Cloud data analysis products, reconstructing interaction logic based on LLM capabilities (e.g., natural language semantic parsing, dynamic knowledge injection) to create a 'zero-code' AI analysis experience covering SaaS and on-premises deployment scenarios.
- Deliver innovative and feasible AI technical solutions based on business needs, leading the development of core modules such as large model fine-tuning (e.g., domain adaptation, parameter-efficient optimization), vector database integration, and intelligent query optimization, ensuring code quality and engineering feasibility.
- Address complex demands from SaaS and on-premises customers by using AI techniques (e.g., model inference optimization, real-time data processing) to resolve performance bottlenecks, semantic ambiguities, and other issues in the intelligent analysis pipeline, guaranteeing stability and accuracy of AI functions across deployment environments.
Tags & Categories
Answer 10 quick questions to check your fit for 腾讯云BI-后台开发工程师 @ Tencent.
10 Questions
~2 Minutes
Instant Score
Related Books and Jobs
腾讯云BI-后台开发工程师
Tencent
腾讯云BI-后台开发工程师
Job Description
腾讯云BI-后台开发工程师
📋 Job Overview
The Backend Development Engineer for Tencent Cloud BI focuses on developing an intelligent analysis platform by leading the architecture design of ChatBI, integrating large model technologies like RAG, NL2SQL, and NL2DSL for natural language-driven data querying and visualization. The role involves AI-driven product design to enhance data analysis products with LLM capabilities, creating zero-code AI experiences for SaaS and on-premises deployments. Responsibilities include implementing AI technical solutions, such as model fine-tuning and vector database integration, and tackling complex issues in intelligent scenarios to ensure performance and stability across environments.
📍 Location: Shenzhen, China
🏢 Business Unit: CSIG
📄 Full Description
1.智能分析平台研发：主导腾讯云ChatBI 的架构设计，深度融合大模型技术（如 RAG、NL2SQL、NL2DSL），实现自然语言驱动的数据查询与可视化分析能力，推动产品向 AI 原生方向升级。
2.AI 驱动产品设计：负责腾讯云数据分析类产品的智能化迭代，基于 LLM 能力重构交互逻辑（如自然语言语义解析、动态知识注入），打造 “零代码” AI 分析体验，覆盖 SaaS 与私有化部署场景。
3.AI 技术方案落地：根据业务需求输出兼具创新性与可行性的技术方案，主导大模型微调（如领域适配、参数高效优化）、向量数据库集成、智能查询优化等核心模块开发，确保代码质量与工程落地性。
4.智能场景问题攻坚：针对 SaaS 与私有化客户的复杂需求，通过 AI 技术手段（如模型推理优化、实时数据处理）解决智能分析链路中的性能瓶颈、语义歧义等问题，保障 AI 功能在不同部署环境下的稳定性与准确性。
2.AI 驱动产品设计：负责腾讯云数据分析类产品的智能化迭代，基于 LLM 能力重构交互逻辑（如自然语言语义解析、动态知识注入），打造 “零代码” AI 分析体验，覆盖 SaaS 与私有化部署场景。
3.AI 技术方案落地：根据业务需求输出兼具创新性与可行性的技术方案，主导大模型微调（如领域适配、参数高效优化）、向量数据库集成、智能查询优化等核心模块开发，确保代码质量与工程落地性。
4.智能场景问题攻坚：针对 SaaS 与私有化客户的复杂需求，通过 AI 技术手段（如模型推理优化、实时数据处理）解决智能分析链路中的性能瓶颈、语义歧义等问题，保障 AI 功能在不同部署环境下的稳定性与准确性。
🎯 Key Responsibilities
- Lead the architecture design of Tencent Cloud ChatBI, deeply integrating large model technologies (e.g., RAG, NL2SQL, NL2DSL) to enable natural language-driven data querying and visualization analysis, advancing the product towards AI-native upgrades.
- Handle AI-driven product design for Tencent Cloud data analysis products, reconstructing interaction logic based on LLM capabilities (e.g., natural language semantic parsing, dynamic knowledge injection) to create a 'zero-code' AI analysis experience covering SaaS and on-premises deployment scenarios.
- Deliver innovative and feasible AI technical solutions based on business needs, leading the development of core modules such as large model fine-tuning (e.g., domain adaptation, parameter-efficient optimization), vector database integration, and intelligent query optimization, ensuring code quality and engineering feasibility.
- Address complex demands from SaaS and on-premises customers by using AI techniques (e.g., model inference optimization, real-time data processing) to resolve performance bottlenecks, semantic ambiguities, and other issues in the intelligent analysis pipeline, guaranteeing stability and accuracy of AI functions across deployment environments.
🛠️ Required Skills
- Proficiency in large model technologies such as RAG, NL2SQL, NL2DSL
- Experience with LLM capabilities including natural language semantic parsing and dynamic knowledge injection
- Skills in large model fine-tuning, domain adaptation, and parameter-efficient optimization
- Knowledge of vector database integration and intelligent query optimization
- Expertise in model inference optimization and real-time data processing
- Strong problem-solving abilities for performance bottlenecks and semantic ambiguities in AI systems
- Backend development skills ensuring code quality and engineering feasibility in SaaS and on-premises environments
Locations
- Shenzhen, China
Salary
Estimated Salary Rangemedium confidence
180,000 - 350,000 CNY / yearly
Source: ai estimated
* This is an estimated range based on market data and may vary based on experience and qualifications.
Skills Required
- Proficiency in large model technologies such as RAG, NL2SQL, NL2DSLintermediate
- Experience with LLM capabilities including natural language semantic parsing and dynamic knowledge injectionintermediate
- Skills in large model fine-tuning, domain adaptation, and parameter-efficient optimizationintermediate
- Knowledge of vector database integration and intelligent query optimizationintermediate
- Expertise in model inference optimization and real-time data processingintermediate
- Strong problem-solving abilities for performance bottlenecks and semantic ambiguities in AI systemsintermediate
- Backend development skills ensuring code quality and engineering feasibility in SaaS and on-premises environmentsintermediate
Responsibilities
- Lead the architecture design of Tencent Cloud ChatBI, deeply integrating large model technologies (e.g., RAG, NL2SQL, NL2DSL) to enable natural language-driven data querying and visualization analysis, advancing the product towards AI-native upgrades.
- Handle AI-driven product design for Tencent Cloud data analysis products, reconstructing interaction logic based on LLM capabilities (e.g., natural language semantic parsing, dynamic knowledge injection) to create a 'zero-code' AI analysis experience covering SaaS and on-premises deployment scenarios.
- Deliver innovative and feasible AI technical solutions based on business needs, leading the development of core modules such as large model fine-tuning (e.g., domain adaptation, parameter-efficient optimization), vector database integration, and intelligent query optimization, ensuring code quality and engineering feasibility.
- Address complex demands from SaaS and on-premises customers by using AI techniques (e.g., model inference optimization, real-time data processing) to resolve performance bottlenecks, semantic ambiguities, and other issues in the intelligent analysis pipeline, guaranteeing stability and accuracy of AI functions across deployment environments.
Tags & Categories
Answer 10 quick questions to check your fit for 腾讯云BI-后台开发工程师 @ Tencent.
10 Questions
~2 Minutes
Instant Score
Related Books and Jobs