This is a fully remote position, open to applicants in Canada.

📋 Description

• Gather and assess performance data of AI models on Intel CPUs and GPUs.

• Contribute to the development of hardware and software features aimed at enhancing AI models and workload efficiency.

• Analyze the effects of optimization on hardware design.

• Assist in the co-design of next-generation Intel CPU and GPU architectures through compiler innovations.

• Collaborate with seasoned engineers on the optimization of AI/ML models and frameworks.

• Acquire practical experience with LLVM, SYCL, CUDA, compilers, and runtimes throughout the hardware-software stack.

⛳️ Requirements

• Currently pursuing a Master's degree or higher in Computer Science, Computer Engineering, Applied Mathematics, or a similar technical discipline, with 2–3 years of relevant hands-on experience gained through internships, academic projects, coursework, or practical training, OR holding a Master's degree in the relevant field without previous professional experience.

• Strong proficiency in C/C++ programming.

• Solid understanding of data structures and algorithms.

• Familiarity with concepts of compiler construction from academic coursework or projects.

• Knowledge of contemporary CPU/GPU architecture and memory systems.

• Experience with accelerated computing and parallel programming models, including OpenMP, CUDA, or SYCL.

• Practical experience in building compilers or compiler components utilizing the LLVM framework.

• Proven ability to analyze and enhance AI models and runtimes for performance and scalability across diverse architectures.

• Experience in kernel programming and optimization of AI models using PyTorch for large language models (LLMs).

• Familiarity with Intel Architecture and methods for performance tracking and analysis of GPUs.

• Demonstrated capability to debug intricate technical issues and proactively suggest solutions.