Edge AI Engineer: Optimize Models for Constrained Devices

Vacaturebank; Eindhoven; Hybrid; EUR 78,000 - 130,000; Full time

Benefits offered by this job

Annual bonus 3%

Health and wellbeing programs

Pension contributions

Discounts on Philips products

Paid leave

Paid parental leave

Job summary

Philips in the Netherlands seeks an Edge AI Engineer to deploy and optimize AI models on constrained edge hardware within medical-device contexts, ensuring performance, safety and regulatory compliance. You will craft efficient inference pipelines, integrate them into product software, and drive quality through rigorous testing and documentation.

Joining a cross-functional team, you will collaborate with software, hardware, cybersecurity and regulatory stakeholders, mentor junior engineers, and

Qualifications

• AI models on edge platforms
• Python with PyTorch or TensorFlow
• Deployment of ML inference pipelines
• Model optimization and profiling
• Experience with embedded/resource-constrained platforms
• MLOps, CI/CD, AI lifecycle management
• AI verification, validation, and risk management in regulated medical-device development
• Signal Processing and Image Processing experience

Responsibilities

• Optimize AI models for edge deployment using TensorRT, OpenVINO, ONNX Runtime, TF Lite
• Profile memory usage, latency, throughput, power and thermal behavior
• Integrate AI inference pipelines into product software architectures
• Contribute to AI verification, validation, risk management, and QMS deliverables
• Collaborate with software, systems, quality, cybersecurity and regulatory teams
• Serve as an expert, provide strategic guidance to influence development practices
• Apply data-driven insights to improve code quality and performance
• Develop APIs and plug-and-play components for AI models across platforms
• Drive continuous improvement and adherence to coding standards across teams
• Keep up-to-date with state-of-the-art programming techniques

Skills

Edge AI on constrained hardware

Python with PyTorch or TensorFlow

ML pipelines deployment

Model optimization & profiling

Embedded platforms

MLOps (ClearML), CI/CD

AI verification, risk management

Signal Processing & Image Processing

Education

Bachelor's / Master's Degree in Computer Science, Software Engineering, Information Technology or equivalent

Job description

Philips in the Netherlands seeks an Edge AI Engineer to deploy and optimize AI models on constrained edge hardware within medical-device contexts, ensuring performance, safety and regulatory compliance. You will craft efficient inference pipelines, integrate them into product software, and drive quality through rigorous testing and documentation.

Joining a cross-functional team, you will collaborate with software, hardware, cybersecurity and regulatory stakeholders, mentor junior engineers, and