Senior Machine Learning Engineer, Perception and Controls

Senior Machine Learning Engineer role supporting Capstan Medical’s robotics and controls team to deliver perception, pose estimation, and FDA-aligned validation for in-procedure medical guidance.

Responsibilities

• Develop registration methods for intraprocedural imaging (fluoroscopy, echocardiography) to the heart valve robot.
• Estimate the pose of catheters and implants from medical images.
• Fuse image-based pose estimates with robot kinematics and additional sensing.
• Quantify uncertainty for each estimate and improve estimate reliability.
• 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 iterate device behavior models from data and collaborate with controls engineers to support control improvements.
• Partner with clinical engineers and physicians to understand procedural imaging, outcomes, and acceptance criteria for accuracy.
• Stay current with the literature, prototype promising approaches, and evaluate what works on Capstan’s datasets.
• Deploy models onto the robot and meet real-time latency budgets.
• Produce validation outputs, test datasets, and design documentation so learned components can pass FDA design controls.

Requirements

• Education: MS in Computer Science, Electrical Engineering, Robotics, or a related field (PhD a plus).
• Experience: 4+ years professional experience in computer vision or machine learning (classical or learned), including at least one system shipped to production on real-world data.
• Experience working with scarce, noisy, or expensive data using approaches such as synthetic data, augmentation, self-supervision, or physics priors.
• Experience applying ML to data from physical systems including 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 offices, with at least 1 day per week in Santa Cruz.

Technologies

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

Preferred Qualifications

• Ultrasound or echocardiography experience (strongly preferred); fluoroscopy or X-ray experience 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, including 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 using ONNX and TensorRT.
• Data platform and MLOps experience, including dataset versioning and experiment tracking.
• Medical device or safety-critical background, including validating ML under FDA design controls.
• Experience as an early ML engineer establishing tools, data practices, and evaluation others build on.
• Publications at venues such as MICCAI, IPCAI, CVPR, ICRA, or IROS.

Skills

• Real-World Machine Learning: shipping models to products that operate on real-world data with noise, drift, and edge cases.
• Computer Vision: classical and learned vision, especially pose estimation, segmentation, tracking, and 2D/3D registration.
• 3D Geometry: rigid transforms, rotations, camera projection models, and calibration.
• Programming: strong Python and PyTorch; comfortable reading and writing C++.
• Data Engineering: building pipelines, datasets, and evaluation harnesses others can trust and reuse.
• Research and Prototyping: turning promising ideas into working prototypes using recent papers as input.
• Problem-Solving: operating with ambiguity by breaking down fuzzy goals into experiments.
• Communication: explaining ML clearly to controls and clinical teams, documenting work effectively, and communicating when a model is good enough to trust.

Benefits

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

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

AI Tools Notice

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