ML Software Developer for FPGA

European Council for Nuclear Research

Geneva, Switzerland

Experience: 3 to 5 Years

Skill Required: IT and ICT

The successful candidate will join the software development for experiments (SFT) group, which develops and provides support for scientific software for the High Energy Physics experiment collaborations at CERN. The selected candidate will work, as part of the Next Generation Trigger (NGT) project, on developing machine learning software for accelerators such as FPGA taking responsibility for developing the hls4ml and Conifer libraries. These libraries have been developed jointly by CERN and its partners. The candidate will deploy neural networks on FPGAs and boosted decision trees using these libraries.

The work will be carried out in an international team of researchers from CERN partner institutes, in the context of the FastML community.

As part of this project, the candidate could be asked to supervise master students.

Your profile

Skills and/or knowledge

  • A solid background in professional programming, with particular emphasis on C++ and high-level synthesis libraries for FPGA programming. 
  • Advanced knowledge of Python programming and existing machine learning tools and techniques, (including network compression).

Eligibility criteria:

  • You are a national of a CERN Member or Associate Member State. 
  • A limited number of positions are also available to candidates from Non-Member States. 
  • You have a professional background in STEM (or a related field) and have either:
  • a Master's degree with 2 to 6 years of post-graduation professional experience;
  • or a PhD with no more than 3 years of post-graduation professional experience.
  • You have never had a CERN fellow or graduate contract before.