You will contribute to exploratory experimental research on AI safety, with a focus on risks from powerful future systems. As a Research Engineer on Alignment Science, you'll work on creating methods to ensure advanced AI systems remain safe and harmless in unfamiliar or adversarial scenarios.

Responsibilities:

• Conduct research on AI control and alignment stress-testing
• Develop and implement new techniques for ensuring AI safety
• Collaborate with other teams, including Interpretability, Fine-Tuning, and the Frontier Red Team
• Test and evaluate the effectiveness of AI safety techniques

Requirements:

• Significant software, ML, or research engineering experience
• Familiarity with technical AI safety research
• Experience contributing to empirical AI research projects

Preferred qualifications:

• Experience authoring research papers in machine learning, NLP, or AI safety
• Experience with LLMs
• Experience with reinforcement learning

Benefits:

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours

Note:

This role requires all candidates to be based at least 25% in London and travel to San Francisco occasionally.

XML job scraping automation by YubHub