Staff Machine Learning Engineer

Intuitive•Sunnyvale, CA

9h•$195,200 - $330,400•Onsite

About The Position

As a Staff Machine Learning Engineer, you will be responsible for developing and delivering novel machine learning solutions for multimodal, physical AI, robotic systems. You will work alongside research, engineering, regulatory, product and clinical teams to develop and test algorithms and translate them into robust, validated and scalable medical device software and infrastructures.

Requirements

PhD or Master’s degree in Computer Science, Electrical Engineering, Robotics, Machine Learning, Computer Vision, or a related technical field.
7+ years of industry experience developing machine learning, robotics, computer vision, simulation, or autonomous-systems software; or 4+ years of industry experience with a PhD
Previously deployed CV/ML projects to users/ customers
Fluent in Python and experience with ML frameworks and models (PyTorch, TensorFlow, JAX), C/C++ (proficiency)
Strong background with hands-on experience of modern deep learning and multimodal vision-language, transformer-based architectures, including self-supervised and predictive foundation-model adaptation and fine-tuning (e.g. JEPA-style models, MAE, DINO, contrastive learning, etc) for improved perception
Proven cross-functional technical leadership in clinical translation (ability to align research, engineering and product stakeholders around an architecture)
Demonstrated ability to lead technically complex ML engineering projects from concept through implementation, validation, and integration with users, engineering platforms, or deployed systems.

Nice To Haves

Familiarity with regulatory-aware AI/ML development, design controls, safety risk analysis, software validation, quality systems, HIPAA, FDA expectations, or data governance in healthcare, medical devices, surgical robotics or other regulated environments.
Familiarity with containerized deployment (Docker, Kubernetes) and scaling ML systems in production
Experience with CI/CD and MLOps pipelines for automated model deployment and monitoring
Proficiency in GPU optimization for either inference or rendering
Track record of publications, patents, open-source contributions, or productized systems in robotics, machine learning, computer vision, medical imaging, surgical robotics, or physical AI.
Experience collaborating with clinicians, clinical advisors, human factors teams, regulatory teams, or product teams to ensure clinically meaningful model performance.

Responsibilities

Independently lead projects to improve key metrics at program-level and product-level of model performance tracked throughout the development life cycle of AI/ ML product solutions
Design, implement and optimize structured experimentation across model architectures, datasets, and training strategies for vision foundation model-driven solutions
Update and improve primary machine learning models - inform and follow through required data collections and testing for both internal and external regulatory milestones.
Optimize and validate models for integration into production systems, ensuring performance in real-world clinical settings. This position will be primarily focused on vision foundation models, but may extend to other (language, action, predictive, physical AI, etc)
Design and maintain end-to-end ML pipelines spanning data collection, data curation, synthetic data generation, model training, evaluation, validation, and integration into robotic platform workflows. Implement semi-supervised and self-supervised methods and pipelines to reduce image annotation burden. Develop tools, pipeline, framework and applications to be deployed and scaled.
Collaborate with physicians and product teams to ensure clinical relevance, robustness and usability of models
Stay up to date with latest CV/ML/VLA/encoding/predictive/generative AI literature, use this to inform research and product direction
Participate in integration of new ML/CV algorithms into existing and future robotic platforms; delivering high-quality, production-ready code in a dynamic and fast-paced environment.