Group Lead Edge AI (human)
- Metzingen, Germany +1
- On-site
- Lead/Staff
- 7+ years
- Master's degree
- Posted
Skills
Required
- TensorRT
- Electrical Engineering
- Embedded Systems
- ML / embedded AI engineering
- common model optimization
- deployment toolchains
- Python
- C++
- PyTorch
- embedded Linux
- low-level profiling
Preferred
- model
- quantization
- NVIDIA
- Jetson
- IQ-series
- model optimization
- pruning
- distillation
- embedded AI hardware platforms
As Group Lead Edge AI, you own the team that turns cutting-edge models into production-grade, on-device intelligence. You set the technical direction, make the hard calls on hardware and architecture, and stay hands-on enough to dive into a profiler when things get tough.
Responsibilities
- Drive on-device AI from research to shipped product.
- Hire, mentor, and grow a team of edge AI engineers into the best in the field.
- Take models from trained to deployed using quantization, pruning, distillation, and every trick it takes to make them fast and lean on embedded accelerator platforms (e.g. NVIDIA Jetson, Qualcomm IQ-series).
- Work with Hardware, Software, and Product to push the limits of what fits in the latency, power, and memory budget you're given.
- Own benchmarking, on-device evaluation, and performance regression testing across every hardware target we ship.
- Debug an accuracy drop after quantization, chase down a latency spike, solve the problem nobody else can.
- What We Can Look Forward To
Requirements
- Cover model export and inference optimization frameworks (e.g. ONNX, TensorRT, AIMET) and the SDKs that turn a model into a working robot behavior.
- An excellent Master's or PhD in Computer Science, Electrical Engineering, Embedded Systems, or a related field.
- 7+ years in ML or embedded AI engineering, with 2+ years leading technically. Real production deployment on embedded accelerators, not just papers.
- Fluency with common model optimization and deployment toolchains (e.g. ONNX, TensorRT, AIMET, or equivalent vendor SDKs).
- Strong Python and C++, PyTorch experience, and comfort with embedded Linux and low-level profiling.
- A conviction that the only real test is the target chip, not the training cluster.
- The ability to lead engineers, make calls under uncertainty, and speak fluently to researchers, hardware engineers, and product alike. Professional English required; German a strong plus (B2 to C1).
Preferred
- Hands-on experience with embedded AI hardware platforms (e.g. NVIDIA Jetson, Qualcomm IQ-series, or comparable).
- Deep expertise in model optimization from the model side to the metal: quantization, pruning, distillation, and architecture search.
