The Joint Real-Time Reconstruction AI Team of the Institute of Experimental Particle Physics (ETP) and the Institute for Information Processing Technology (ITIV) at the Karlsruhe Institute of Technology (KIT) invites applications for postdoctoral positions in real-time track reconstruction and the deployment of machine learning algorithms on embedded processors. 

As part of the ErUM-Data DEEP consortium (erumdata-deep.de ), you will prototype real-time Graph Neural Network algorithms for the Belle II tracking detectors, implement them on heterogeneous hardware including AMD Versal SoCs and Coarse Grain Reconfigurable Architecture AI cores, and contribute to a common transpiler toolchain based on ONNX and MLIR. Successful candidates will have the opportunity to spend part of their time working on accelerated ML applications on GPUs or other hardware, or the Belle II physics program.

Your profile:

• PhD in Electrical Engineering, Computer Science, Particle Physics, or a related field preferred
• Experience in applying machine learning beyond basic data analysis
• Experience with HDL languages (VHDL/Verilog), FPGA toolchains (Vivado), PCIe/AXI interfaces, and hardware-software co-design
• Excellent English communication and presentation skills, and publication record
• Experience supervising undergraduate students 
• Experience documenting project progress
• Willingness and ability to travel as required, including to Japan