Senior AI System Engineer - LLM Training System
Huawei Technologies Canada Co., Ltd. · Posted Nov 3, 2026
- Vancouver, British Columbia, Canada
- Full-time · Senior
- $127K–$225K per year
- 3+ years
Lead development of high-performance compute operators and distributed training systems for large foundation models on Huawei Ascend NPUs.
Compensation
The total target annual compensation ranges from $127,000 to $225,000 depending on education, experience, and demonstrated expertise.
Responsibilities
- Design, implement, and tune core operators using AscendC, Triton, and TileLang
- Architect, scale, and optimize distributed pre‑training and post‑training pipelines using MindSpeed and upstream frameworks
- Tune multi‑dimensional hybrid parallelism and RL rollout pipelines on Ascend NPU clusters
- Conduct deep performance profiling on Ascend hardware to eliminate bottlenecks
- Contribute high‑performance operators and acceleration features to open‑source Ascend communities
Requirements
- Bachelor’s, Master’s, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or related technical disciplines
- Nice to have: Experience porting Triton or TileLang to non‑CUDA accelerators
- Nice to have: Deep understanding of Ascend NPU microarchitecture
- Nice to have: Low‑precision numerical alignment expertise
- Nice to have: Open‑source contributions to Ascend or upstream projects