Current Vacancies

Engineer (Operating Room Scene Understanding)

手术室场景理解研究-工程师

Job Responsibilities

1. Implement and optimize scene graph-based operating room understanding systems.  

2. Engineer multimodal fusion and dynamic scene modeling for object detection, relationship inference, and semantic annotation.  

3. Deploy scene graphs for workflow analysis, behavior understanding, and device interaction modeling.  

4. Build efficient multi-view data processing and geometric alignment pipelines.   

5. Support technology transfer and system delivery for research outcomes.  

Requirements

1. Master's/bachelor's degree in computer science, software engineering, or related fields (exceptional undergraduates considered).  

2. Experience in scene graph generation, object detection, relationship modeling, or semantic annotation.  

3. Knowledge of multi-view geometry (camera calibration, SfM, MVS).  

4. Proficiency in AI frameworks (PyTorch, HuggingFace Transformers) and coding.  

5. Strong engineering skills in multimodal data processing and system development.  

Preferred Qualifications

1. Experience in scene graph generation/reasoning.  

2. Familiarity with multimodal LLMs (CLIP, BLIP, LLaVA, InternVL, QwenVL).  

3. Background in operating room research (behavior analysis, workflow recognition).   

4. Experience in medical imaging, surgical video analysis, or video summarization.  

5. Knowledge of privacy-preserving techniques and medical data security.  

Application Method

Please send your resume to hr02@cair-cas.org.hk. Please indicate [Engineer (Operating Room Scene Understanding)]-[Name] in the subject of your email.

岗位职责

1. 实现基于多视角场景图（Scene Graph）的手术室场景理解系统，优化场景图生成与推理算法；

2. 工程化实现多模态数据融合与动态场景语义建模，支持手术室目标检测、关系推理与语义标注；

3. 将场景图生成算法应用于手术流程分析、医生行为理解和设备交互建模；

4. 搭建高效的多视角数据处理与几何对齐管线，支持动态场景解析；

5. 支持科研项目成果的技术落地与系统交付。

职位要求

1. 计算机科学、软件工程或相关专业硕士及以上学历（优秀本科生亦可考虑）；

2. 熟悉场景图生成与推理相关技术，有目标检测、关系建模或语义标注开发经验；

3. 熟悉多视几何基础（如相机标定、SfM、MVS 等），能够将多视角数据用于场景图生成；

4. 熟练掌握人工智能算法开发主流框架（如 PyTorch, Huggingface Transformers, LLaMA Factory）及相关工具，具备良好的代码开发能力；

5. 有实际系统开发经验，擅长多模态数据处理与工程化实现；

6. 能够独立解决问题，完成高质量系统开发任务。

优先考虑

1. 有场景图生成 / 推理方面的经验。

2. 熟悉多模态大语言模型（CLIP, BLIP, LLaVA, InternVL, QwenVL）。

3. 有手术室研究方面的背景（行为分析、工作流程识别）。

4. 具有医学影像、手术视频分析或视频总结方面的经验。

5. 了解隐私保护技术以及医学数据安全方面的知识。

申请方式

请将简历发送至 hr02@cair-cas.org.hk。邮件主题请注明应聘 [手术室场景理解研究-工程师]-[姓名]。