Senior AI/ML Research Engineer (Computer Vision)
Core
Develop perception models for an Embodied-AI system to understand surgical scenes, extracting anatomy, instruments, and actions from intraoperative video to enable safe, real-time robotic control.
Role type
Senior AI/ML Research Engineer (Computer Vision)
Builds
Perception models and algorithms for next-generation robotic surgical platforms.
Domain
Medical robotics / Surgical AI / Computer Vision
Deliverable
production ML models
Required skills
Computer vision research, deep learning (CNNs, vision transformers), video understanding (temporal action segmentation, video transformers), self-supervised learning, Python, C++, PyTorch/TensorFlow/JAX, data curation, loss design, model evaluation
Preferred skills
Healthcare/medical device background, Sim-to-real workflows, robotics simulators (NVIDIA Isaac), multimodal fusion, real-time/edge inference optimization (TensorRT, Jetson), fine-grained interaction modeling, peer-reviewed publications
Technologies
PyTorch, TensorFlow, JAX, NVIDIA Isaac, TensorRT, NVIDIA Jetson
Responsibilities
Develop temporal models for activity and workflow understanding; benchmark in-house models against state of the art; define perception input/output specifications; establish continuous-improvement loops with human-in-the-loop relabeling; partner with data teams to shape label taxonomies and pipelines; drive research-to-deployment path for real-time integration.
Seniority
Senior, hands-on IC
