Edge AI Engineer for Real-Time Embedded Mobility

XpertDirect; Helsinki; On-site; EUR 90,000 - 130,000; Full time

Job summary

XpertDirect in Helsinki is seeking an experienced Edge AI Software Engineer to build software that runs ML models directly on embedded hardware. You will develop high-performance C++ software for real-time edge applications and optimise models for constrained devices.

Collaborating with ML, Embedded, and Systems teams, you will deploy TensorFlow Lite/ONNX workflows on ARM-based platforms, ensure efficient memory and power usage, and improve reliability of edge AI systems in real-world tests.

Qualifications

• 4+ years in Embedded Software, Edge AI, Embedded Linux or related roles.
• Commercial Embedded Linux software development experience.
• Experience with ARM-based hardware.
• Hands-on deployment/optimisation of ML models for edge devices.
• Python development for automation, testing or ML workflows.
• Understanding of memory, CPU latency and power constraints.
• Strong Linux debugging and performance-analysis skills.

Responsibilities

• Deploy ML models onto ARM-based embedded platforms.
• Develop high-performance C++ software for real-time edge apps.
• Optimise TensorFlow Lite models for latency and memory usage.
• Integrate AI inference into Embedded Linux applications.
• Build software that processes sensor/vehicle data at the edge.
• Profile and optimise model performance on constrained hardware.
• Develop Python tooling for model conversion, testing and deployment.
• Collaborate with ML engineers to move models from experiments to production.

Skills

Embedded Software

Edge AI

C++

Python

Linux

Machine Learning

Tools

ARM-based hardware

TensorFlow Lite

ONNX Runtime

NVIDIA Jetson

Buildroot/Yocto

CAN / Automotive Ethernet

Job description

XpertDirect in Helsinki is seeking an experienced Edge AI Software Engineer to build software that runs ML models directly on embedded hardware. You will develop high-performance C++ software for real-time edge applications and optimise models for constrained devices.

Collaborating with ML, Embedded, and Systems teams, you will deploy TensorFlow Lite/ONNX workflows on ARM-based platforms, ensure efficient memory and power usage, and improve reliability of edge AI systems in real-world tests.