Job Description 岗位职责： 1.协助处理物理系统的历史实验数据（如洗净比、水电消耗等），并将高维控制参数转化为图结构数据（Graph-Structured Data），维护相关的图数据库。Assist in processing historical experimental data from physical systems (e.g., wash index, energy/water consumption) and transforming high-dimensional control parameters into Graph-Structured Data. Manage and query related graph databases. 2.参与深度核学习/高斯过程代理模型的搭建、训练与调优，提升模型在高维参数空间的预测精度。Participate in the construction, training, and fine-tuning of the Deep Kernel Learning / Gaussian Process) surrogate model. Optimize the model to and improve prediction accuracy in high-dimensional parameter spaces. 3.协助团队进行相关领域的文献检索与梳理，参与顶会学术论文的实验设计、图表绘制等工作。Assist with literature reviews, experiment design, data visualization for top-tier conference submissions. 教育背景： 计算机科学、人工智能、应用数学或相关专业的硕士及以上学历 Specific Expertise 特定专业知识： 1.熟练掌握 Python，具备在 Linux 环境下的开发经验；熟练使用 PyTorch 深度学习框架及相关库（如 PyTorch Geometric）。High proficiency in Python and solid experience developing in a Linux environment. Hands-on experience with deep learning frameworks, specifically PyTorch and related libraries (e.g., PyTorch Geometric). 2.具备扎实的机器学习基础，对以下至少一个方向有深入理解或实践经验： 图神经网络（GNN）、频繁子图挖掘（FSM）、贝叶斯优化（BO）、高斯过程（GP）或主动学习（Active Learning）Solid background in machine learning with a deep understanding or practical experience in at least one of the following areas: Graph Neural Networks (GNNs) or Frequent Subgraph Mining (FSM), Bayesian Optimization (BO), Gaussian Processes (GP), or Active Learning. 3.具备良好的英语阅读和写作能力，学习能力强，有团队合作精神及强烈的科研驱动力。Strong English reading and writing skills. Highly self-motivated, with strong learning capabilities and a collaborative team spirit. 4.熟练的英语能力 5.曾在 IJCAI、AAMAS、AAAI、NeurIPS 等 AI 顶级会议或期刊上发表过论文，或有完整参与顶会论文投稿的经验。 Previous experience submitting to or publishing in top-tier AI conferences/journals (e.g., IJCAI, AAMAS, NeurIPS, AAAI)