Researcher – Parallel Computing

About the role

The AnShi Lab at Huawei Canada is seeking a researcher to advance parallel computing techniques for its network gateway policy engine. You will explore GPU and heterogeneous CPU/GPU solutions to improve rule‑lookup performance and scalability.

Key responsibilities

• Analyze performance and scalability limits of the current network gateway policy engine and develop parallel algorithms for rule lookup and incremental updates on GPUs, heterogeneous CPU/GPU, or multi‑core CPU systems.
• Investigate hybrid CPU/GPU architectures inspired by high‑speed DPI and pattern‑matching systems.
• Design and evaluate novel data structures for efficient network‑gateway rule matching.
• Implement and optimise solutions in C/C++ to production‑quality standards, ensuring performance, robustness and maintainability.
• Collaborate with product and malware‑research teams to integrate the new engine into real products and contribute to patents and publications.
• Participate in additional malware‑research projects as required.

Required profile

• Ph.D. (preferred) or Master’s degree in Computer Science, Electrical & Computer Engineering, Mathematics or a related field, with a focus on systems, high‑performance computing or databases, or equivalent research experience.
• Demonstrated experience with at least two of the following: hybrid CPU/GPU systems, parallel computing, high‑performance computing, SIMT, AI compilers, GPU programming (CUDA, HIP, OpenCL) or other accelerators.
• Strong C/C++ programming skills with a track record of writing performance‑critical code.
• Solid understanding of algorithms, data structures and computer architecture (caches, memory hierarchy, etc.).
• Additional experience in malware analysis, machine‑learning models (LLM, GNN) or TCP/IP network stack is a plus.

Required skills

• C/C++ programming
• GPU programming (CUDA, HIP, OpenCL)
• Parallel and high‑performance computing
• SIMT programming model
• AI compiler technologies
• Algorithms and data structures
• Computer architecture (caches, memory hierarchy)
• Malware analysis (optional)
• Machine‑learning fundamentals (LLM, GNN)
• TCP/IP network stack knowledge