AI Safety & Scheming Eval Scientist/Engineer

COL Limited; City Of London; On-site; GBP 100,000 - 200,000; Full time

Job summary

A leading research organization in London seeks Research Scientists and Engineers to conduct safety evaluations and collaborate with top-tier AI labs like OpenAI and Google DeepMind. Ideal candidates should have a strong foundation in empirical research, excellent communication skills, and software engineering experience in Python. The role is full-time, with competitive salary and extensive benefits including unlimited vacation and professional development budget.

Benefits

Flexible work hours

Unlimited vacation

Paid work trips

Yearly professional development budget

Qualifications

• Experience in empirical research related to AI control and evaluations.
• Strong scientific writing and communication skills.
• Comprehensive experience in LLM steering.

Responsibilities

• Conduct safety evaluations and develop theoretical frameworks.
• Collaborate with frontier labs on pre-deployment evaluations.
• Automate the evals pipeline.

Skills

Experience in empirical research

Excellent scientific writing

Experience in LLM steering

Software engineering skills

Tools

Python

Inspect (evals framework)

Job description

A leading research organization in London seeks Research Scientists and Engineers to conduct safety evaluations and collaborate with top-tier AI labs like OpenAI and Google DeepMind. Ideal candidates should have a strong foundation in empirical research, excellent communication skills, and software engineering experience in Python. The role is full-time, with competitive salary and extensive benefits including unlimited vacation and professional development budget.