Research Engineer In Automated Machine Learning Toronto

Join Preference Model as a Research Engineer specializing in automated ML and RL environments. Help shape the future of self‑directed learning by building robust training infrastructures. In this role, you'll be at the intersection of research and engineering, pushing the boundaries of post‑training on large language models.

You will train and evaluate models using proprietary RL environments, architect infrastructure, and implement methodologies for RL agents. Your contributions will have a direct impact on data quality and model capabilities.

Key Responsibilities

• Train and evaluate models on proprietary RL environments
• Architect and optimize RL training infrastructure
• Design and test training environments and evaluation methodologies
• Profile and optimize training runs for maximum throughput

Requirements

• Experience with end-to-end LLM post‑training pipelines
• Proficiency in Python and PyTo...