AI Safety Researcher (Machine Learning Specialization)

Responsibilities

• Help clarify AI safety research questions central to the "Scientist AI" program
• Analyze proposed solutions and develop new ideas
• Propose, design, and implement new ML algorithms and experiments to solve complex AI safety problems
• Evaluate the program's integration into a broader strategic vision for AI risk mitigation
• Communicate complex results to other researchers and developers

Requirements

• Research experience in technical AI safety, ideally with a focus on AGI safety
• Experience proposing, designing, and executing ML experiments
• Proficiency in ML frameworks such as PyTorch or TensorFlow
• Ability to work in a collaborative environment and communicate complex results
• PhD in a relevant field preferred (or equivalent exceptional experience)

Preferred Qualifications

• Research experience in agent foundations, AI control, frontier AI safety, latent knowledge extraction, or outsourced reasoning
• Research publications in top-tier ML venues (e.g., NeurIPS, ICML, ICLR)
• Experience in language model refinement and post-training

Benefits

• Comprehensive health benefits
• Minimum of 20 vacation days from start
• Minimum 4% employer retirement savings contribution
• Generous and flexible benefits designed for well-being
• Collaborative and inclusive work environment

About the Company

LoiZéro is a non-profit organization dedicated to advancing research and developing technical solutions for safe AI systems. Based in Montreal, LoiZéro conducts research to design non-agentic AI systems that learn to understand the world through transparent probabilistic reasoning, inspired by the methods of Professor Yoshua Bengio.