As a deep-tech startup, we are looking for talented and passionate people with an appetite for problem solving. Besides the minimal requirements for this job position, your profile is a good fit to our company if you have the following values:
- High flexibility and adaptability.
- Tranquility to work under pressure.
- Appetite for learning and problem solving.
- Critical thinking.
- Ability to communicate effectively.
- Keen to collaboration.
- Proper time management.
- Highly autodidact, independent and proactive.
Responsibilities:
- Actively participate in the planning and execution of the compiler deployment of the 10 Million cores SpiNNcloud Machine.
- Participate in the development of the neural network compiler for SpiNNaker2.
- Merge the partition and configuration manager (PACMAN) for SpiNNaker with the machine learning graph compiler.
- Work closely with the applications team to assess and optimize applications deployed at different hierarchy levels of the SpiNNcloud machine.
- Participate in the inclusion of energy-based optimization methodologies into the neural network compiler.
- Port the SpiNNaker software stack into common open source machine learning compiler frameworks.
- Derive specifications to improve the hardware and software interaction within the SpiNNcloud machine.
- Technical documentation of the results and exploration process across all experiments.
Minimum Requirements:
- Solid understanding of low-level and intermediate representation (IR) for high-level optimization in neural network compilers.
- Experience porting backends into open source machine learning compiler frameworks such as Apache TVM or TensorFlow XLA.
- Strong programming skills and development experience in C and C++, involving data structures, graphs and object oriented programming.
- More than 5 years of experience working with kernel optimizations, dataflow analysis, parallelization, scheduling or memory allocation.
- BSc, MSc or Dipl.-Ing. in Computer Science, Electrical Engineering, Computer Engineering, or any other related computationally intensive field.
Added value:
- Being an active contributor in Github or any other hosting software development with version control.
- Programming knowledge in Python is desirable.
- Experience with the SpiNNaker1 software stack is a significant differentiator.
- Experience with energy estimation methodologies (e.g., Accelergy) for accelerators.
- Experience with latency- and energy-based characterization tools (e.g., Timeloop) to define optimal mappings in large-scale architectures.
- Experience with the LLVM compiler and toolchain.
- Experience with Agile Methodologies.
- Dr.-Ing., or PhD in Computer Science, Electrical Engineering, Computer Engineering, or any other related computationally intensive field.
We offer a highly competitive salary with reallocation benefits in a flexible and inclusive work environment. We are an equal opportunity employer, and hence we welcome people of different backgrounds, nationalities and experiences.