Edge AI Engineer (Embedded ML / Real-Time Inference)

About

We’re partnering with a well-funded, mission-driven engineering company developing next-generation intelligent systems operating in highly constrained, real-world environments. Their work sits at the intersection of edge AI, robotics, and advanced autonomy with a strong emphasis on reliability, efficiency, and performance under pressure.

This is an opportunity to work on cutting-edge embedded AI systems where cloud access is not guaranteed, and every millisecond and watt matters.

The Role

As an Edge AI Engineer, you will take ownership of deploying machine learning models onto embedded and resource-constrained hardware, ensuring real-time performance in production environments.

You’ll work closely with perception, robotics, and systems engineers to bridge the gap between research models and robust, field-ready deployments.

Core Responsibilities

• Own the end-to-end pipeline from trained ML models to real-time inference on embedded systems
• Optimise neural networks for deployment on constrained hardware (GPU, ARM, FPGA, or custom accelerators)
• Convert and deploy models using tools like TensorRT, ONNX, and CUDA
• Develop high-performance inference pipelines in C++ for real-time applications
• Integrate perception models into larger systems (e.g. robotics or autonomous platforms)
• Diagnose and resolve performance bottlenecks including latency, memory usage, and thermal constraints
• Benchmark and validate models directly on hardware in realistic operating conditions
• Ensure systems are robust, reliable, and capable of running fully offline

Technical Requirements

• Strong experience with C++ and performance-critical systems
• Hands-on experience deploying ML models to edge devices
• Familiarity with TensorRT, ONNX, PyTorch, or similar frameworks
• Experience with GPU acceleration (CUDA) or other hardware-specific optimisation
• Experience working in Linux-based environments and embedded systems

Nice to Have

• Experience with ROS or robotic systems integration
• Exposure to embedded platforms such as Jetson, ARM, or FPGA-based systems
• Background in robotics, autonomous systems, aerospace, or defence environments
• Experience working with custom hardware or accelerators

Hybrid/Onsite

Bavaria, Germany