Senior AIML Research Engineer (Computer Vision)

Primary Function of Position

We are building advanced augmented dexterity capabilities for next-generation robotic platforms. As a Senior AI/ML Research Engineer (Computer Vision) you will develop the perception models that let our Embodied-AI system understand the surgical scene. Working within a hierarchical multimodal stackwhere a high-level model interprets sensory observations into structured intent and a low-level policy turns that intent into precise safe real-time controlyou will focus on the vision layer: designing training and evaluating models that extract anatomy instruments actions and surgical context from intraoperative video. You will partner with the broader AI/ML team to define how perception feeds reasoning and control and you will drive the research-to-deployment path for your models taking them from offline experimentation to robust real-time performance in the OR.

Working within Intuitives Future Forward research organization you will identify build and finetune the AI/ML models and algorithms that enables us to deliver safe and performant embodied AI systems. This role calls for someone who is equally comfortable getting hands-on with models and data and designing systems that scale.

Roles and Responsibilities

• Develop temporal models for activity and workflow understanding: event/state recognition and fine-grained temporal action segmentation.
• Benchmark in-house models against the state of the art and recommend the target perception architecture.
• Define the perception input/output specification and demonstrate offline feasibility on recorded data.
• Stand up a continuous-improvement loop (discrepancy flagging active learning human-in-the-loop relabeling) and the tooling/UI needed for offline evaluation and the path to real-time use.
• Partner with annotation and data teams to shape label taxonomies QC and the data pipeline that feeds the AI/ML models.
• Establish the path from offline evaluation on recorded data to real-time integration including the continuous-improvement (human-in-the-loop) data loop.
• Partner with AI/ML researchers robotics data engineers and other stakeholders to deliver a perception layer that enables rapid prototyping and learning while working toward a product solution.

Qualifications :

Minimum Qualifications

• MS or PhD in CS EE Robotics or a related field with 5 years of applied computer-vision research experience.
• Strong grasp of modern CV and deep-learning fundamentals: CNNs and vision transformers segmentation detection tracking and representation/self-supervised learning.
• Demonstrated work in video understanding including temporal action segmentation action/phase recognition and video segmentation.
• Hands-on experience with modern video architectures including video transformers and self-supervised video pretraining.
• Exposure to vision-action (VA) / vision-language-action (VLA) models and world-model / self-supervised predictive architectures (e.g. JEPA-style models MAE DINO) for learning visual representations and dynamics.
• Experience working with large messy real-world video datasets at scale.
• Strong software and experimentation skills in Python and C with proficiency in one or more of PyTorch/TensorFlow/JAX and the ability to stand up clean reproducible experiments and run the full loop (data curation augmentation loss design metrics error analysis).
• A research-and-prototyping mindset: comfortable working in ambiguity framing open-ended problems running rapid experiments and reading and reproducing recent papers to pull promising techniques into practice.
• Sound judgment about the path from prototype to product: writing code others can build on knowing when to optimize versus when to move fast and thinking ahead about data quality evaluation and robustness even at the research stage.
• Solid foundations in linear algebra probability and optimization enough to reason about and debug model behavior from first principles.
• Comfort collaborating across a multidisciplinary team (ML robotics software and clinical/domain experts) and communicating tradeoffs and findings clearly.

Preferred Qualifications

• Background in healthcare medical devices surgical robotics or other regulated technical domains.
• Sim-to-real workflows and experience with robotics simulators (e.g. NVIDIA Isaac)
• Experience with structured ontology- or taxonomy-based labeling frameworks for fine-grained activity.
• Multimodal fusion of video with sensor telemetry and system-log streams.
• Designing annotation pipelines QC processes and active-learning loops.
• Real-time / edge inference optimization (e.g. TensorRT NVIDIA Jetson).
• Fine-grained interaction and object-relationship modeling.
• Relevant peer-reviewed publications (CVPR ICCV ECCV NeurIPS etc.).

Additional Information :

Due to the nature of our business and the role please note that Intuitive and/or your customer(s) may require that you show current proof of vaccination against certain diseases including COVID-19.  Details can vary by role.

Intuitive is an Equal Opportunity Employer. We provide equal employment opportunities to all qualified applicants and employees and prohibit discrimination and harassment of any type without regard to race sex pregnancy sexual orientation gender identity national origin color age religion protected veteran or disability status genetic information or any other status protected under federal state or local applicable laws.

Mandatory Notices

U.S. Export Controls Disclaimer:  In accordance with the U.S. Export Administration Regulations (15 CFR 743.13(b)) some roles at Intuitive Surgical may be subject to U.S. export controls for prospective employeeswho are nationals from countries currently on embargo or sanctions status.

Certain information you provide as part of the application will be used for purposes of determining whether Intuitive Surgical will need to (i) obtain an export license from the U.S. Government on your behalf (note: the governments licensing process can take 3 to 6 months) or (ii) implement a Technology Control Plan (TCP) (note: typically adds 2 weeks to the hiring process).  

For any Intuitive role subject to export controls final offers are contingent upon obtaining an approved export license and/or an executed TCP prior to the prospective employeesstart date which may or may not be flexible and within a timeframe that does not unreasonably impede the hiring need. If applicable candidates will be notified and instructed on any requirements for these purposes. 

We will consider for employment qualified applicants with arrest and conviction records in accordance with fair chance laws.

Preference will be given to qualified candidates who do not reside or plan to reside in Alabama Arkansas Delaware Florida Indiana Iowa Louisiana Maryland Mississippi Missouri Oklahoma Pennsylvania South Carolina or Tennessee.

This position may be filled at a different job level than listed here depending on
business need and/or on the selected candidates experience knowledge and skills.
Compensation will be based primarily on the job level at which the role is filled and the
candidates qualifications consistent with applicable law.

We provide market-competitive compensation packages inclusive of base pay incentives benefits and equity. It would not be typical for someone to be hired at the top end of range for the role as actual pay will be determined based on several factors including experience skills and qualifications. The target compensation ranges are listed.

Remote Work :

No

Employment Type :

Full-time