SR HIGH-PERFORMANCE SOFTWARE ENGINEER
Description
We are looking for a candidate to join a team whose goal is developing a high-performance and energy-efficient code targeting a novel HW-accelerator with thousands of cores. You will be able to evaluate the performance of the implemented algorithms in Machine Learning and Artificial Intelligence use cases, either in functional emulators or in real silicon. You will be helping in establishing the foundations and processes of a fastly growing SW team.
Responsibilities
- Have an impact in the team developing high efficient code targeting a novel AI-accelerator
- Interaction with the AI-accelerator to depurate functionality and performance
- Develop code to automatically generate highly optimized code
- Interact with functional emulators and real silicon
Minimum Qualifications
- MS in Computer Science or a related technical field
- Knowledge of object-oriented programming and STLs
- Good understanding of parallel programming and vectorization
- Business fluent English
Desired Qualifications
- 3+ years of experience developing in C++ and parallel languages (CUDA/OpenMP/MPI)
- PhD in Computer Science
- Understanding of Machine Learning algorithms and Neural Networks
- Good knowledge of profiling & debugging tools/frameworks
- Strong knowledge of processor and SOC architecture
- Good foundation of coherence and consistency memory models
- Understanding GCC and LLVM compiler infrastructure
- Understanding of compiler optimizations and memory profilers
- Strong knowledge of C++ coding best practices, writing robust leak/crash free code
- Experience in Python or other scripting languages
- Experience with basic GitLab-CI or other CI pipeline flows