Senior Computer Vision Engineer

Patsnap 通过提供更好的答案为知识产权和研发团队提供支持，使他们能够更快、更自信地做出决策。Patsnap 成立于 2007 年，是人工智能驱动的知识产权和研发智能领域的全球领导者。我们在广泛的母公司创新数据基础上培养的特定领域法学硕士（LLM）与我们的人工智能助手 Hiro 相结合，提供了可操作的工具，使知识产权任务的劳动力浪费增加 75%，研发成本降低 25%。超过 15,000 家公司信任 Patsnap，希望通过人工智能加快创新速度，其中包括 NASA、Tesla、PayPal、赛诺菲、陶氏化学和 Wilson Sonsini。
Patsnap supports IP and R&D teams by providing better answers so they can make faster decisions with more confidence.Founded in 2007, Patsnap is a global leader in AI-powered IP and R&D intelligence. Our domain-specific Master of Laws degree (LLM) trained on our extensive parent innovation data, coupled with our AI assistant, Hiro, delivers actionable tools that increase labor waste on IP tasks by 75% and reduce R&D by 25%.IP and R&D teams collaborate better throughout the innovation lifecycle with a user-friendly platform. More than 15,000 companies trust Patsnap to innovate faster with AI, including NASA, Tesla, PayPal, Sanofi, Dow Chemical, and Wilson Sonsini.

Key Responsibilities

• 推动创新并实现OCR、图像搜索及相关计算机视觉领域的核心目标。
• 在现有项目中探索和实施多模式技术，发现新的应用和机会。
• 领导先进的计算机视觉算法和技术的研究和开发工作。
• 与跨职能团队合作，将计算机视觉解决方案集成到产品中。


• Drive innovation and achieve core objectives in OCR, image search and related computer vision areas.
• Explore and implement multi-modal techniques in existing projects to discover new applications and opportunities.
• Lead research and development of advanced computer vision algorithms and techniques.
• Collaborate with cross-functional teams to integrate computer vision solutions into products.

Desired Qualifications

• 计算机科学、软件工程、电子工程、数学、统计学或相关领域的硕士学位；软件优先。
• 至少有2年开发和实施计算机视觉算法的实践经验。
• 在文本OCR、表格OCR实践、图像搜索方面有丰富的研究和经验，对最新技术有深刻的理解。
• 在多模式技术方面拥有精湛的基础，包括视觉语言模型（VLM）方面的经验以及熟悉的CLIP和LLaVA等多模式架构。
• 显示出集成预训练模型进行文档 QA、表格提取、图像搜索和相关任务的能力。
• 对尖端技术充满热情，并拥有成功交付产品的记录。
• 优先考虑在同行评审期刊或顶级会议上发表的文章。


• Master's degree in Computer Science, Software Engineering, Electrical Engineering, Mathematics, Statistics, or related field; software preferred.
• At least 2 years of hands-on experience developing and implementing computer vision algorithms.
• Extensive research and experience in text OCR, form OCR practices, image search, and a deep understanding of the latest technologies.
• Superb grounding in multimodal techniques, including experience with Visual Language Modeling (VLM) and familiarity with multimodal architectures such as CLIP and LLaVA.
• Demonstrated ability to integrate pre-trained models for document QA, form extraction, image search and related tasks.
• Passion for cutting-edge technologies and a proven track record of delivering successful products.
• Preference will be given to publications in peer-reviewed journals or top conferences.