Job Details

Computer Vision and Machine Learning Engineer, Co-op

Join to apply for the Computer Vision and Machine Learning Engineer, Co-op role at Neptune Medical.

Neptune Medical, a venture-backed medical device company based in Silicon Valley, designs, manufactures, and commercializes innovative medical devices using proprietary Dynamic Rigidization technology. Our first FDA-cleared device, Pathfinder, is used at leading U.S. hospitals and academic centers. We are developing a fully flexible medical robot, Triton Robotic Endoscopy, to revolutionize flexible endoscopy and improve patient outcomes.

Position Details

• Title: Computer Vision and Machine Learning Engineer, Co-op
• Duration: 6-9 months
• Start Date: Summer 2025

Role Summary

We seek a motivated Computer Vision and Machine Learning Co-Op to develop deep learning models for analyzing complex data from our medical robots. Responsibilities include working with synthetic and real-world video and multi-modal data to create solutions that enhance the accuracy, efficiency, and safety of robotic-assisted medical procedures. The role involves designing, developing, and clinically validating ML algorithms for medical robotic applications.

Responsibilities

• Develop AI solutions to improve clinical outcomes in flexible endoscopy.
• Create and manage synthetic datasets and simulation environments to bridge the Sim-to-Reality Gap.
• Develop tools for annotation and validation of large medical datasets.
• Utilize open-source models for rapid prototyping and clinical evaluation.

Minimum Qualifications

• Strong communication and presentation skills.
• B.S. or M.S. in Computer Science, Data Science, Mathematics, or related fields.
• Relevant coursework in Computer Vision and Deep Learning.
• Proficiency in Python.
• Experience with CV and ML tools: OpenCV, PyTorch or TensorFlow, ONNX, TensorRT.
• Experience with simulation tools like Blender, IsaacSim, Mujoco.
• Solid understanding of computer vision techniques: image segmentation, feature detection, optical flow, SLAM, 3D reconstruction.
• Knowledge of deep learning inference profiling and model debugging.

Preferred Qualifications

• Specialization or minor in AI or Machine Learning.
• Experience with GPU programming libraries such as Nvidia Warp or Taichi.
• Data engineering experience: preprocessing, tracking, storage.
• Experience with model validation and failure diagnosis.
• Proficiency in C++ and GPGPU programming (CUDA, OpenCL).

Additional Details

Location: Burlingame, CA, near Millbrae Caltrain and BART Station.

Pay: Starting hourly rate between $31.00 and $38.00, dependent on experience and other factors. Potential eligibility for 401(K) matching.

We are an equal opportunity employer committed to diversity and inclusion.