Co‑op Researcher – LLM Post‑Training & Agentic Coding

About the role

Huawei Canada is seeking a Co‑op Researcher to join the Noah’s Ark Laboratory in Edmonton. The intern will work on advanced research topics such as large language model post‑training, reinforcement learning, reasoning, and agentic coding, turning hypotheses into rigorous experiments.

Key responsibilities

• Design and execute research on LLM post‑training, agent training, task synthesis, and environment generation.
• Build and evaluate intelligent agents capable of reasoning, tool use, code generation, and solving complex real‑world tasks.
• Develop scalable infrastructure for LLM training, inference, agent rollout, and synthetic data generation.
• Improve GPU‑based post‑training and inference workflows, including distributed execution and automation.
• Collaborate with researchers and engineering teams to prototype ideas, reproduce state‑of‑the‑art methods, and translate research into practical systems.

Required profile

• Enrolled in a senior Bachelor’s, Master’s or PhD program in Computer Science, Machine Learning, AI or a related field.
• Strong fundamentals in machine learning, deep learning, and large language models.
• Hands‑on experience with LLM post‑training, reinforcement learning, or ML infrastructure.
• Ability to define open‑ended problems, design experiments, and drive projects to measurable results.
• Highly self‑motivated, intellectually curious, and able to work in a fast‑moving research environment.

Required skills

• Python programming
• PyTorch framework
• Docker and Linux environments
• Git version control
• Multi‑GPU compute (e.g., FSDP, DeepSpeed)
• Familiarity with vLLM, SGLang, Hugging Face libraries