Senior Machine Learning Engineer, Perception and Controls

Capstan Medical, Inc. is building robotics and controls for cardiac healthcare, and this role sits within the team that turns intraprocedural imaging into actionable perception. You will help develop real-time registration and pose estimation for devices inside a patient, while also producing the validation and design documentation needed to meet FDA design controls.

In this senior position, you will work across perception, data, and deployment so that learned components can run on a robotic system with strict latency requirements. The work spans end-to-end ownership, from model and data pipeline development to testing, documentation, and practical feedback from clinical partners.

What you will do

• Develop methods to register intraprocedural imaging, such as fluoroscopy and echocardiography, to the robot.
• Estimate the pose of catheters and implants from medical images.
• Fuse image-based estimates with robot kinematics and other sensing, and quantify uncertainty for each estimate.
• Build data pipelines to capture, align, label, and version imaging and robot data for training and evaluation.
• Use simulation and synthetic data when real clinical data is limited.
• Fit and improve models of device behavior from data and collaborate with controls engineers to enhance control.
• Partner with clinical engineers and physicians to understand what the images show, what matters during the procedure, and what accuracy is sufficient.
• Read relevant literature, prototype promising ideas, and clearly communicate what works and what does not on Capstan’s data.
• Deploy models on the robot while meeting real-time latency budgets.
• Write validation materials, test datasets, and design documentation to support FDA design controls for learned components.

Requirements

• MS in Computer Science, Electrical Engineering, Robotics, or a related field; PhD is a plus.
• 4+ years of professional experience in computer vision or machine learning (classical or learned), including at least one system shipped to production on real-world data.
• Experience handling scarce, noisy, or expensive data, using approaches such as synthetic data, augmentation, self-supervision, or physics priors.
• Experience building machine learning systems on data from physical platforms such as robots, cameras, medical imaging, or sensors.
• Ability to thrive in a fast-paced environment and own problems end-to-end.
• Ability to work onsite 3–4 days per week, split flexibly between Santa Cruz, CA and West Menlo Park, CA, with at least 1 day per week in Santa Cruz.

Technologies

• Python, PyTorch, C++, ROS, ROS2
• ONNX, TensorRT
• Kalman filters, factor graphs

Workplace details

• Location: West Menlo Park, CA (hybrid)
• Workplace type: Hybrid, onsite 3–4 days per week across Santa Cruz and West Menlo Park, CA, with at least 1 day per week in Santa Cruz
• Reports to: Robotics & Controls Manager

Benefits

• Outstanding benefits with medical, dental, and vision covered at 100% for you and your family, plus flex time off.
• Fun, fast-paced, collaborative environment focused on transformational technologies in cardiac healthcare.
• Work-hard, play-hard culture with office outings.

Preferred qualifications

• Ultrasound or echocardiography experience, strongly preferred; fluoroscopy or X-ray experience is also valuable, including 2D/3D registration or digitally reconstructed radiographs.
• Experience tracking catheters, needles, surgical tools, or continuum robots in images.
• Sensor fusion and state estimation experience (for example, Kalman filters or factor graphs).
• System identification or learned dynamics for control, including residual models on top of physics.
• Robotics software experience with ROS/ROS2 and on-device inference under latency constraints (ONNX, TensorRT).
• Data platform and MLOps experience, including dataset versioning and experiment tracking practices.
• Medical device or safety-critical background, including validating ML under FDA design controls.
• Experience as an early ML engineer on a team, setting up tools, data practices, and evaluation others can build on.
• Publications at venues such as MICCAI, IPCAI, CVPR, ICRA, or IROS.

AI tools notice

Capstan Medical may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist the recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans.