The Surgical Devices team's mission is to democratize surgery and empower surgeons with the goal of better surgical outcomes for patients. Together, with industry partners and clinical experts, we are building an end-to-end solution for cloud-connected surgical devices to collect and process surgical data at scale, and to derive actionable insights for pre-op planning, intra-op guidance and post-op education and training. Our portfolio combines on-devices software for data collection and real-time analysis, advanced imaging algorithms and tools, cloud services for data processing and state-of-the-art machine learning, as well as web and mobile apps for our various stakeholders.
- Develop safe, efficient software (opportunities in Rust, C++, and Python) for managing surgical video between our endoscope, machine learning models, and networking platform.
- Build a holistic system: the on-device surgical team is small, and there are many cross-cutting opportunities for ownership (image processing, ML, networking, device management, security, and more).
- Benchmark and optimize a system running directly on hardware, analyzing and providing input on hardware and software configurations which will end up in Operating Rooms around the world.
- Collaborate extensively across the surgical subteams, including the imaging group (AIG), the ML-focused oscopies team in Israel, and the Surgical Analytics team, responsible for cloud-based technologies.
- BS degree in Computer Science, Computer Engineering or related technical field, or equivalent practical experience with 5+ years of software development experience in one or more general purpose.
- Experience with one or more of Rust, C++, Python.
- Linux Systems experience: able to create, profile, and debug software effectively.
- Willingness to learn/grow, and respectfulness that allows colleagues to do the same.
- Familiarity with TensorFlow, or similar ML frameworks.
- Familiarity with GPU-based technologies (CUDA, OpenCV).
- Experience using containers, or other similar technologies for isolation and reproducibility.
- Familiarity with Linux Networking stack, able to debug cross-platform data pipelines.