Research Scientist/Engineer — Frontier AI & Evaluation

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

Benefits offered by this job

Market competitive salary

Equity options

Flexible work hours

Unlimited vacation

Provided meals on workdays

Paid work trips

Yearly professional development budget

Job summary

A leading AI research organization in London seeks Research Scientists and Engineers to develop the 'Science of Scheming.' This role involves collaborating with AI developers, studying complex AI dynamics, and creating evaluation techniques. Candidates should possess strong skills in empirical research, analytical reasoning, and software engineering, preferably with experience in training LLMs. The role offers competitive compensation, flexible work hours, and a dynamic work environment.

Qualifications

• Design and execute experiments, striving for speed in iterations.
• Familiar with the problem of AI scheming and existing literature.
• Hands-on experience in training LLMs via reinforcement learning.
• Strong quantitative skills from fields like statistical physics.

Responsibilities

• Collaborate with leading AI developers on various models.
• Study RL dynamics and model organisms to gain insights.
• Develop evaluation techniques for advanced AI models.
• Analyze and extract patterns in reasoning from AI systems.

Skills

Fast-paced empirical research

Conceptual insights about scheming

Software engineering skills

Intense interest in AI progress

Experience RL-training LLMs

Strong analytical skills

Tools

Python

Job description

A leading AI research organization in London seeks Research Scientists and Engineers to develop the 'Science of Scheming.' This role involves collaborating with AI developers, studying complex AI dynamics, and creating evaluation techniques. Candidates should possess strong skills in empirical research, analytical reasoning, and software engineering, preferably with experience in training LLMs. The role offers competitive compensation, flexible work hours, and a dynamic work environment.