Senior MLOps Engineer - Edge

📋 Description

• Build scalable Edge infrastructure to deploy models to fleets of devices.
• Own the model compilation platform and optimise hardware-specific inference engines.
• Collaborate with Data Scientists, Embedded Engineers, and Product Managers.
• Drive automation, telemetry, and reliability for production models in the wild.
• Address edge-specific constraints like low bandwidth, limited storage, and network failures.
• Mentor and lead by establishing best practices in Python tooling, IaC, and CI/CD.

🎯 Requirements

• Production MLOps with CI/CD, Docker, and Linux experience.
• Edge inference and compilation know-how; TensorRT; FP16/INT8; calibration and engine validation.
• Collaborative, systems-thinking mindset; ability to work with researchers and embedded engineers.
• Experience designing architectures for 10,000+ devices with canary releases and safe rollbacks.
• Bias toward action and initiative to help the team win.
• Experience with edge AI stacks is a plus (NVIDIA Jetson, DeepStream, TensorRT).

🎁 Benefits

• Flexible work life with remote options and holiday planning.
• Autonomy in your work with a supportive culture.
• Opportunities for career growth and professional development.
• Resources and environment to succeed, regardless of location.
• Wellbeing support and employee resource groups where available.