Staff AI/ML Software Engineer – Navigation R&D

Purpose

As a Staff AI/ML Software Engineer in the Navigation R&D team, you will architect, plan and lead the AI/ML development and integration for next-generation surgical navigation and planning systems. You will serve as the technical bridge between AI/ML and software engineering teams, assisting the software teams with translating models into production-grade, maintainable software components. You'll collaborate closely with a cross-functional team of software, systems, hardware, firmware, quality, and regulatory partners to deliver safe, reliable, and scalable software that directly impacts patient outcomes.

Job Responsibilities

• Be a key contributor in the evolution of DePuy Synthes' AI/ML platform for flexible machine learning model training, fine-tuning, transformation and evaluation across surgical navigation initiatives, driving model improvements using the latest techniques.
• Build and integrate production ready, on-device and cloud-based AI/ML models into the navigation software product, owning model packaging, versioning, and deployment while meeting real-time performance, latency, memory, and compute constraints.
• Co-Lead definition, development, and maintenance of APIs and data contracts between ML components and the navigation software, partnering with software engineers to ensure models are testable, maintainable, and verifiable within the product.
• Contribute to regulatory documentation, traceability, and V&V aligned with IEC 62304, ISO 14971, and related guidance; support submissions (e.g., FDA 510(k)) as needed.
• Contribute to product planning and Agile/Scrum delivery, lead design/code reviews to sustain long-term maintainability, and mentor engineers.

Required Qualifications

• BS/MS in Machine Learning, Artificial Intelligence, Computer Science, Computer Engineering, or a related field
• 8+ years of overall software engineering experience, including 5+ years delivering machine learning models into production software (or equivalent)
• Significant hands-on experience developing, optimizing, and deploying ML models for image-based inference (e.g., classification, object detection, segmentation, landmark/pose estimation) in production software
• 2+ years of participating in a scrum team as an AI/ML software SME, with excellent communication, collaboration, and technical influence skills
• Proven ability to lead architecture and design reviews
• Highly proficient in Python, with strong object-oriented design, design patterns, and unit/integration testing skills
• Proven experience with developing, deploying, and maintaining AI/ML processes in a large user base production environment (Enterprise MLOps experience a huge bonus)
• Demonstrable expertise in ML frameworks (TensorFlow, Keras, PyTorch, scikit-learn, etc.) and ML model training/optimization, both local and cloud (AWS SageMaker, Azure Machine Learning studio)
• Experience developing AI systems in regulated environments (e.g., SaMD), such as surgical, medical imaging, or healthcare-related AI/ML applications, across the full SDLC: requirements, design, implementation, testing, technical documentation, traceability, validation, release, and maintenance

Preferred Qualifications

• Demonstrated experience in multiple types of AI technologies beyond traditional Machine Learning (Agentic AI, Generative AI, LLMs), including AI-driven development and testing
• Experience developing machine learning models using various input data types beyond static images (point clouds, numerical data, text data, etc.)
• Experience with production .NET (C#) API development
• Experience with requirements, design documentation in tools like Polarion, JAMA, etc.