Frontier AI Evaluation Scientist

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

Benefits offered by this job

Market competitive salary

Equity options

Unlimited vacation

Paid staff retreats and conferences

Yearly professional development budget

Job summary

A leading AI evaluation firm in Greater London seeks a software engineer to evaluate cutting-edge AI models. You will run pre-deployment evaluations, analyze AI behaviors, and improve evaluation pipelines. Candidates should possess strong Python skills, process optimization experience, and the ability to derive insights from complex datasets. This full-time position offers a competitive salary and flexible working arrangements, contributing to innovative AI research.

Qualifications

• Strong software engineering experience with Python.
• Experience in process optimisation and improving workflows.
• Ability to extract insights from large datasets.

Responsibilities

• Run pre-deployment evaluation campaigns on AI systems.
• Analyze model transcripts to surface behavioral patterns.
• Build new evaluations for frontier risks.

Skills

Software engineering skills

Process optimisation

Data Analysis & Pattern Recognition

Writing and communication

AI power-user

Job description

A leading AI evaluation firm in Greater London seeks a software engineer to evaluate cutting-edge AI models. You will run pre-deployment evaluations, analyze AI behaviors, and improve evaluation pipelines. Candidates should possess strong Python skills, process optimization experience, and the ability to derive insights from complex datasets. This full-time position offers a competitive salary and flexible working arrangements, contributing to innovative AI research.