Intern Engineer – RL Post-Training for LLMs

About the role

Huawei Canada’s Computing Data Application Acceleration Lab is seeking an Intern Engineer to develop and optimize reinforcement‑learning post‑training pipelines for large language models. This role offers hands‑on experience in cutting‑edge LLM research within a collaborative, full‑stack innovation environment.

Key responsibilities

• Develop and optimize RL post‑training pipelines for LLMs (e.g., GRPO, reward modeling).
• Conduct experiments to improve model performance, reasoning, and alignment.
• Build scalable training, evaluation, and data‑generation systems.
• Collaborate with researchers and engineers on advanced LLM projects.
• Stay current with advancements in RL, LLMs, and post‑training research.

Required profile

• Enrolled as a Master’s or Ph.D. student in Computer Science, AI, or a related field.
• Strong background in machine learning, reinforcement learning, and deep learning.
• Familiarity with large language models, transformer architectures, and post‑training methods.

Required skills

• Python programming.
• PyTorch deep‑learning framework.
• Experience with LLM frameworks and libraries (e.g., Hugging Face, DeepSpeed, vLLM, SGLang).
• Hands‑on work with RL training algorithms such as GRPO.
• Knowledge of RL frameworks like VeRL.
• Understanding of domain‑specific languages used with AI accelerators.
• Experience with distributed training frameworks and large‑scale experimentation.
• Familiarity with LLM infrastructure and data‑generation pipelines.

What we offer

• Target annual compensation ranging from $58,000 to $104,000 CAD, based on education, experience, and demonstrated expertise.
• A commitment to a fair, inclusive, and accessible recruitment process, with accommodations available as needed.