Research Scientist

📋 Description

• Execute technical research in AI safety by designing and running experiments to study and steer
• Apply white-box and black-box interpretability methods, focusing on transformers and LLMs.
• Develop modular, reproducible research code in Python using PyTorch.
• Build and maintain research infrastructure and tooling to accelerate discovery.
• Document findings via academic papers, technical reports, and presentations.
• Collaborate with senior scientists to refine hypotheses and identify research scope.

🎯 Requirements

• Solid background in machine learning fundamentals and transformer architectures (LLMs).
• Experience with interpretability techniques (steering vectors, mechanistic interpretability).
• Strong Python programming, PyTorch, and Git for version control.
• Excellent communication to translate results into clear reports.
• Curiosity and analytical rigor with exposure to AI safety areas (robustness, evaluation

🎁 Benefits

• Hybrid Working
• Unlimited Annual Leave
• Private healthcare and dental
• Enhanced parental leave
• Family-Friendly Flexibility
• Sanctus Coaching