Computational / Machine Learning Lead(J24812)

1. 01

   主导AI药物发现方向的机器学习算法架构设计与技术选型，搭建适配药物研发场景的AI/ML技术体系 Lead the architecture design and technology selection of machine learning algorithms for AI drug discovery, and build an AI/ML technical system adapted to pharmaceutical R&D scenarios.

2. 02

   带领团队完成生成式AI、深度学习、图神经网络等模型在药物发现场景的研发与落地，覆盖基于结构的药物设计（SBDD）、基于配体的药物设计（LBDD）等核心场景 Lead the team to develop and deploy generative AI, deep learning, GNN and other models for drug discovery scenarios, covering core areas including structure-based drug design (SBDD) and ligand-based drug design (LBDD).

3. 03

   搭建MLOps工程体系，基于云平台（AWS/GCP）实现算法模型的高效迭代、部署与规模化运行 Establish the MLOps engineering system, and realize efficient iteration, deployment and large-scale operation of algorithm models based on cloud platforms (AWS/GCP).

4. 04

   对接药物研发业务需求，推动算法模型落地验证，确保模型输出能够在湿实验室中得到有效验证，产出真实的药物发现hit结果 Align with pharmaceutical R&D business requirements, promote the validation of algorithm models, and ensure model outputs can be effectively verified in wet labs to deliver real drug discovery hits.

5. 05

   跟踪AI制药领域前沿技术，持续优化技术方案，提升药物发现的效率与成功率 Track cutting-edge technologies in the AI pharmaceutical field, continuously optimize technical solutions, and improve the efficiency and success rate of drug discovery.

基础要求 | Basic Requirements 学历：计算机科学、计算生物学、机器学习等相关专业，本科及以上学历（硕士、博士优先） Education: Bachelor’s degree or above in Computer Science, Computational Biology, Machine Learning or related fields (Master’s or Ph.D. preferred). 经验：3年及以上AI药物发现领域相关工作经验，有算法落地到真实药物研发流程的实践经验 Experience: 3+ years of relevant work experience in AI drug discovery, with practical experience in deploying algorithms to real pharmaceutical R&D workflows. 技术能力要求 | Technical Competencies 精通Python编程语言，熟练使用PyTorch、TensorFlow等主流深度学习框架 Proficient in Python programming language, and skilled in mainstream deep learning frameworks such as PyTorch and TensorFlow. 掌握生成式AI、机器学习、深度学习、图神经网络（GNNs）等核心算法，有药物设计相关算法研发经验 Master core algorithms including generative AI, machine learning, deep learning and Graph Neural Networks (GNNs), with experience in algorithm development for drug design. 熟悉RDKit等药物研发计算工具，了解基于结构的药物设计（SBDD）、基于配体的药物设计（LBDD）相关原理与应用 Familiar with pharmaceutical R&D computing tools such as RDKit, and understand the principles and applications of structure-based drug design (SBDD) and ligand-based drug design (LBDD). 具备MLOps相关实践经验，有AWS或GCP云平台上部署、运维机器学习模型的经验优先 Have practical experience in MLOps; experience in deploying and maintaining machine learning models on AWS or GCP cloud platforms is preferred. 加分项 | Preferred Qualifications 有已落地的机器学习模型项目，且模型成果成功转化为湿实验室验证的药物发现hit（需提供真实落地成效证明，非纯SaaS工具或学术论文成果） Proven track record of deployed machine learning models that have successfully translated into wet-lab validated drug discovery hits (proof of real-world efficacy is required, not just SaaS tools or academic paper outputs). 我们欢迎这样的你 | What We Look For 深耕AI制药领域，对算法落地有深度理解，不局限于理论研究 Deep expertise in the AI pharmaceutical field, with a thorough understanding of algorithm deployment beyond theoretical research. 有强烈的目标感，能够推动技术方案在真实药物研发场景中验证价值 Strong goal orientation, with the ability to drive technical solutions to deliver validated value in real drug discovery scenarios. 有跨领域协作意识，能够对接药物研发、湿实验团队，共同推进项目落地 Cross-domain collaboration awareness, able to work with pharmaceutical R&D and wet-lab teams to jointly advance project implementation.