Research Engineer - LLM Training & Alignment Systems
Kingston, ONOn-siteContract
Huawei Technologies Canada Co., Ltd.
Candidates need hands-on experience training and aligning large language models, including SFT, reward modelling and PPO or GRPO. They also need large-scale distributed training experience across GPU or NPU hardware, LLM evaluation experience, and proficiency in Python, C/C++ or Go.
GPU, NPU