Senior Research Engineer (Hardware Accelerators)

Join Code Metal as a Senior Research Engineer specializing in hardware accelerators. In this role, you will design and develop code transpilation and optimization pipelines for various hardware accelerators, collaborate with multidisciplinary teams, and present research findings to a broader audience. You will need strong programming skills in Python and C/C++, a good understanding of popular hardware devices, and at least 5 years of industry experience. Benefits include relocation assistance, health care plan, uncapped vacation, flexible hybrid work arrangement, and retirement plan.

• Collaborate with researchers and engineers to design and develop code transpilation and optimization pipelines for various hardware accelerators.
• Understand the architecture of the target hardware and propose optimization strategies that would accelerate given input code.
• Conduct experiments to evaluate performance of code transpilation and optimization pipelines, and analyze experimental results to improve pipelines further.
• Strong programming skills in Python and C/C++
• Ability to translate technical research into practical engineering solutions
• Good understanding of popular hardware devices such as CPUs and GPUs
• Excellent communication skills and a collaborative mindset
• Good understanding of parallel programming languages: CUDA/OpenCL/OpenMP/SYCL
• Combination of strong software engineering skills with a solid background in high-performance computing to build robust and maintainable systems
• Demonstrated proficiency in core software development practices, including: version control, code review, testing, continuous integration, build systems, and release pipelines
• 5+ years of industry experience and an advanced degree (Master’s or Ph.D.) in Computer Science, Mathematics, or a related field, with a focus on software engineering, high-performance computing, and parallel programming languages
• Understanding of AI-specific hardware accelerators such as NPUs is a plus
• Good understanding of common performance analysis practices
• Understanding of the latest AI-specific hardware accelerators such as NPUs, Google TPUs
• Familiarity with deep learning frameworks such as PyTorch and TensorFlow
• Experience integrating parallel programming tools into CI/CD pipelines or software development workflows
• Contributions to related open-source projects
• Experience working in high-assurance industries (e.g., aerospace, medical devices, automotive)