Edge AI Engineer(m/w/x)

Beschreibung

You will bridge the gap between research and production by optimizing high-performance AI models for edge devices, ensuring hardware-accelerated pipelines remain fast and secure.

Anforderungen

• •Strong proficiency in Python
• •Expert-level knowledge of C/C++
• •Familiarity with Rust or C
• •In-depth understanding of model optimizations
• •Hands-on experience with PyTorch
• •Experience with ONNX Runtime
• •Experience with embedded platforms
• •Proficient knowledge of Embedded Linux
• •Exceptional problem-solving skills
• •Ability to work independently

Aufgaben

• •Deploy and scale AI models across diverse hardware fleets
• •Optimize models for edge runtimes using quantization and pruning
• •Develop robust architectures for real-time data processing
• •Optimize CUDA kernels specifically for xLSTM architectures
• •Manage hardware resources for ultra-low latency inference
• •Profile and debug performance bottlenecks across the stack
• •Collaborate with researchers to build scalable AI architectures
• •Prioritize data privacy and system integrity at the edge
• •Manage complex data flows and end-to-end security mechanisms

Tools & Technologien

Benefits