Principal AI/ML Engineer

Abbott; Santa Clara (CA); On-site; USD 149,000 - 297,000; Full time

Job summary

Abbott Vascular seeks a Principal AI/ML Engineer to advance OCT-based intravascular imaging with scalable, clinically relevant algorithms. You will own end-to-end ML lifecycle from data prep to deployment in regulated medical devices, collaborating across clinical, imaging, and software teams.

Focus areas include semantic segmentation, image analysis, and real-time inference optimization, leveraging cutting-edge ideas such as foundation models and self-supervised learning while ensuring design

Qualifications

• Masters or PhD in a related field with AI/ML focus.
• 8 years in ML/DL or 4 years with PhD, in industry.
• Strong experience with image analysis: segmentation, detection, classification.
• Proficiency in Python and ML frameworks (PyTorch, TensorFlow).
• Ability to translate research to production-grade software.

Responsibilities

• Design, develop, and deploy ML/DL models for OCT image analysis.
• Lead semantic segmentation algorithm development for OCT vascular imaging.
• Own end-to-end ML lifecycle from data prep to deployment.
• Collaborate with clinical and V&V teams on metrics and validation.
• Develop robust algorithms for diverse patient data and imaging conditions.
• Optimize models for real-time or near real-time inference.
• Contribute to software architecture and design controls documentation.

Skills

Deep learning architectures

Vision transformers

Python programming

Model validation

Experiment design

Cross-functional collaboration

Education

Master’s or PhD in Computer Science, Electrical Engineering, Biomedical Engineering, or related field with AI/ML focus

Tools

PyTorch

TensorFlow

ONNX

TensorRT

TorchScript

Job description

Position Overview :

Abbott Vascular is seeking a Principal AI/ML Engineer to develop advanced machine learning solutions for optical coherence tomography (OCT)–based intravascular imaging systems. This role will focus on developing robust, clinically relevant algorithms to automatically identify and characterize key anatomical and interventional features. The successful candidate will translate cutting‑edge AI research into scalable, high‑performance solutions integrated into regulated medical device products. The role requires close collaboration with clinical, imaging, software, and systems engineering teams throughout the product development lifecycle.

Key Responsibilities

• Design, develop, and deploy machine learning and deep learning models for clinical applications, including image segmentation, feature detection, classification, and quantitative analysis of OCT images.


• Lead the development of advanced semantic segmentation algorithms for OCT‑based vascular imaging applications.


• Own the end‑to‑end ML lifecycle, including data preparation, annotation strategies, model development, training, validation, performance optimization, and deployment.


• Collaborate with clinical and V&V teams to define clinically meaningful outputs, evaluation metrics, and validation methodologies.


• Develop algorithms capable of robust performance across diverse patient populations, imaging conditions, and clinical use cases.


• Optimize models for real‑time or near‑real‑time inference in embedded or product environments.


• Evaluate and integrate state‑of‑the‑art machine learning approaches, including foundation models, self‑supervised learning, and generative AI techniques where appropriate.


• Contribute to software architecture, code reviews, and engineering best practices to ensure scalable and maintainable AI solutions.


• Generate technical documentation supporting design controls, verification, validation, risk management, and regulatory submissions.

Required Qualifications

• Master’s or Ph.D. in Computer Science, Electrical Engineering, Biomedical Engineering, or a related field with a focus on AI/ML.


• 8 years of industry experience developing machine learning, deep learning, or computer vision solutions, or 4 years of relevant industry experience with a PhD.


• Strong expertise in deep learning architectures and modern machine learning approaches for image analysis, including convolutional neural networks and vision transformers


• Proven experience developing semantic segmentation, object detection, classification, and image analysis algorithms.


• Strong programming skills in Python and experience with ML frameworks such as PyTorch, TensorFlow, or equivalent.


• Experience designing experiments, evaluating model performance, and applying statistical methods for model validation.


• Demonstrated ability to translate research concepts into prototype and production‑quality software solutions.


• Excellent communication and cross‑functional communication skills.

Preferred Qualifications

• Experience with OCT, IVUS, CT, MRI or other medical imaging modalities, including multi‑modal image registration techniques.


• Understanding of OCT imaging principles, image formation physics, and common imaging artifacts.


• Experience developing AI/ML solutions for 3D volumetric, temporal, longitudinal or sequential imaging datasets.


• Experience with foundation models, generative AI, self‑supervised learning, multimodal learning, or other advanced AI approaches applied to medical imaging.


• Expertise in model deployment and optimization for real‑time or near‑real‑time inference using technologies such as ONNX, TensorRT, TorchScript, or equivalent frameworks.


• Experience establishing scalable MLOps workflows, including data and model versioning, experiment tracking, continuous integration/deployment, and production ML pipelines.


• Familiarity with medical device software development processes in regulated environments, including FDA regulations, design controls, V&V, and AI/ML‑related FDA guidelines.


• Demonstrated ability to translate research‑grade algorithms into robust, production‑ready solutions for clinical or commercial applications.

The base pay for this position is $148,700.00 — $297,300.00. In specific locations, the pay range may vary from the range posted.