Job Description

PURPOSE/SUMMARY

:


We are currently seeking a Senior Computer Vision Engineer to join our top-notch Research & Development team. This is an exciting time to join us and to be part of a leading edge team that is pioneering a new era of Performance-Guided Surgery. You will help lead the development of a next-generation vision-assisted surgical robotics platform. As a researcher on the team, you will get a chance to work alongside some of the best minds in the field and implement the latest Machine Learning and Computer Vision algorithms, in a multidisciplinary and dynamic environment. We are looking for an individual who is a team player and a strong communicator. Someone who has great problem-solving skills, and who has a drive for creativity and innovation, as well as determination and persistence. Someone who has a deep understanding of algorithms and image processing and will take ownership of various Vision/deep learning/AI algorithms utilizing medical imaging data & sensory data through exploration, development, optimization, validation & integration.

ESSENTIAL DUTIES, RESPONSIBILITIES AND AUTHORITY:

Work with a multi-disciplinary team of experts and engineers to deliver an end-to-end product: from the idea phase, through collecting and assessing the data, exploring algorithmic approaches, developing, testing, validating and integrating the algorithm in the production environment Design and implement deep learning models to detect and classify various scenes, activities, and human-object interactions. Experiment with architectures such as CNNs, RNNs, transformers, and hybrid models suited for video tasks. Work on multimodal models if combining video data and other sensors. Contribute to the team's methodologies, best practices and toolset, as well as sharing and receiving constructive feedback Understand algorithmic requirements and convert these into usable solutions Utilize existing research, literature and study of existing state of the art tools to develop best in class solutions Develop mathematical and numerical tools to support development Manage large amounts of data and process into usable information Evaluate the performance on benchmarks and improve as necessary

MINIMUM COMPETENCE (EDUCATION, EXPERIENCE, AND SKILL) REQUIREMENTS:

QUALIFICATIONS:

MSc in Computer Science or related fields (EE, Math, Physics, etc.); Ph.D - Advantage. 5+ years of hands-on experience with Computer Vision algorithms. Strong background in machine learning and deep learning. Proficiency in C++ and Python. Ability to initiate and lead machine learning projects end to end. Experience with TensorFlow or PyTorch Familiarity with IPP, OpenCV and similar libraries Deep domain experience and hands-on knowledge or academic research background in at least one of the following is an advantage: ?

1. GNN


2. Scene Understanding


3. Video Understanding


Experience with Linux. Ability to work in a team environment Good verbal and writing capabilities in English Read and understand the relevant literature and professional terms Teamwork and high communication skills

ADDITIONAL KNOWLEDGE, SKILLS AND ABILITIES (OPTIONAL):

Experience with using LMM/VLM(Vision-Language) frameworks - Advantage. Familiar with ML tools such as W&B or ClearML - Advantage. Experience in a global medical device company - Advantage. * Work in a multidisciplinary environment of the surgical robotic system