Edge AI Engineer (human)

The role

You will turn cutting-edge models into production-grade, on-device intelligence for robots. You will work at the intersection of machine learning, embedded systems, and robotics to make models fast, lean, and reliable on hardware.

What you will do

• Deploy models at the edge using quantization, pruning, and distillation on embedded accelerator platforms.
• Work across model export and inference optimization frameworks and SDKs.
• Profile, analyze, and tune models and runtimes to meet latency, power, and memory budgets.
• Partner with Research, Hardware, Software, and Product teams.
• Build and maintain benchmarking, on-device evaluation, and performance regression testing.
• Debug accuracy drops, latency spikes, and problems on the real chip.

Required qualifications

• Master's or PhD in Computer Science, Electrical Engineering, Embedded Systems, or a related field.
• 3+ years in ML or embedded AI engineering with real production deployment on embedded accelerators.
• Hands-on experience with embedded AI hardware platforms like NVIDIA Jetson or Qualcomm IQ-series.
• Solid knowledge of model optimization including quantization, pruning, distillation, and architecture search.
• Fluency with common model optimization and deployment toolchains like ONNX, TensorRT, or AIMET.
• Strong Python and C++ experience.
• PyTorch experience.
• Comfort with embedded Linux and low-level profiling.
• Professional English required.

Nice to have

• German is a strong plus (B2 to C1)

About the company

neura-robotics-gmbh