Build the future of AI-driven drug discovery 共建 AI 驱动新药发现 的未来

Core of the DTBL Design loop. You will develop and deploy generative models for structure-aware 3D molecular design, directly powering all four pipeline programs. DTBL Design 环节核心。你将开发并部署结构感知三维分子生成模型，直接驱动四条管线。

Core of the DTBL Learn loop. You will build and maintain multi-task SAR models and ADMET prediction pipelines that route every generated molecule through a druggability filter before synthesis. DTBL Learn 环节核心。你将构建并维护多任务 SAR 模型与 ADMET 预测管线， 对每个生成分子在合成前完成成药性过滤。

The hidden core of the DTBL loop. You will own dry-wet experiment data standardization, feature engineering, and version management — the data quality layer that determines whether our AI models improve or stagnate. Industry data shows 68% of AI projects fail due to poor data quality; this role exists to ensure GenTide is not one of them. DTBL 闭环的隐性核心。你将负责干湿实验数据标准化入库、特征工程与版本管理—— 这一数据质量层决定我们的 AI 模型是持续进步还是停滞不前。 行业数据显示 68% 的 AI 项目因数据质量差而失败；这个岗位就是为确保睿联不是其中之一。

The wet-lab backbone of the GLP-1 and β2-AR programs. You will translate AI-designed peptide sequences into synthesized, characterized compounds — closing the Design → Test loop and feeding real activity data back into our models. GLP-1 与 β2-AR 管线湿实验的核心支撑。你将把 AI 设计的多肽序列转化为合成、表征完备的化合物，闭合 Design → Test 循环，并将真实活性数据反哺模型迭代。

Responsible for crude peptide purification, refining, and freeze-drying — providing qualified peptide products for drug discovery and ensuring compliance with domestic and international regulatory standards. 负责多肽药物粗肽的纯化、精制、冻干等工艺，为新药发现提供质量合格的多肽产品，确保产品质量符合国内外法规要求。

Critical to the Nav1.8 and TKI programs. You will take AI-proposed small molecule scaffolds from design to synthesized candidate — independently owning route design, multi-step synthesis, and process scale-up through to IND-enabling studies. Nav1.8 与 TKI 管线的关键角色。你将把 AI 提出的小分子骨架从设计推进至合成候选物，独立主导路线设计、多步合成及工艺放大，直至支持IND申报。

The analytical quality layer that keeps the DTBL loop honest. You will build and own the purity, assay, and impurity characterization methods that validate every synthesized compound — the data backbone for both internal decision-making and IND regulatory submissions. 保障 DTBL 闭环数据可信度的分析质量层。你将构建并主导纯度、含量及杂质表征方法，验证每一个合成化合物——为内部决策与IND法规申报提供数据基础。

Responsible for screening drug physiological activity — identifying candidate substances with expected pharmacological activity on specific biological targets through systematic and standardized experimental methods. This role lays the foundation for preclinical and clinical research, reduces R&D risk, and directly feeds activity data back into the DTBL loop. 负责药物生理活性筛选，通过系统化、规范化的实验手段甄别出对特定生物靶点具有预期药理活性的候选物质，为后续临床前与临床研究奠定基础，降低研发风险、提高新药发现效率，并将真实活性数据直接反哺DTBL闭环。

The DTBL loop runs on software. You will design and build the internal platform that connects AI models, wet-lab workflows, and data pipelines into a single coherent system — making it faster and safer to iterate from molecule design to experimental result. This is a generalist engineering role with high ownership: you will work across backend services, internal tooling, and cloud infrastructure. DTBL 闭环依赖软件运转。你将设计并构建连接 AI 模型、湿实验工作流与数据管线的内部平台—— 让从分子设计到实验结果的每一次迭代更快、更可靠。 这是一个高度自主的全栈工程岗位，涵盖后端服务、内部工具与云基础设施建设。

As an AI Agent Engineer, you will design and implement autonomous agentic workflows that orchestrate our drug discovery models. You will be responsible for creating robust systems where LLMs interact with complex scientific tools, databases, and APIs. 作为 AI 智能体工程师，你将设计和实现自主智能体工作流，以编排我们的药物发现模型。你将负责创建稳健的系统，让大语言模型（LLM）与复杂的科学工具、数据库和 API 进行交互。

A founding-stage company runs on the people and systems that hold it together. You will be the operational backbone — keeping the team focused on science by owning HR workflows, IP filing coordination, government liaison, and the day-to-day infrastructure that lets researchers do their best work. 创始阶段的公司靠人和系统运转。你将是运营核心——通过主导人事流程、专利申请协调、政府对接与日常基础设施管理，让科学家们专注于研发本身。