Research Scientist/Engineer (Evaluations)

Apollo Research(2 days ago)

London, United KingdomOnsiteFull TimeSenior$135,000 - $270,000Research & Development

About this role

Apollo Research is seeking a candidate to rigorously test frontier AI models through evaluation campaigns, analyze behavioral patterns, and improve evaluation pipelines. The role involves collaboration with leading AI labs and working on assessments that address AI risks like scheming.

View Original Listing

Required Skills

Python
Data Analysis
Automation
Pattern Recognition
AI Models
Evaluation
Research
Software Engineering
Pipeline Development
Automation

About Apollo Research

apolloresearch.ai

Apollo Research is an independent AI safety research organization focused on reducing dangerous capabilities in advanced models, with particular emphasis on deceptive or “scheming” behaviors. They design model evaluations and conduct interpretability research to better understand state-of-the-art systems and detect emerging risks. Their governance team also provides technical guidance to global policymakers and stakeholders to help shape safer deployment and oversight as AI systems become more widely integrated.

View more jobs at Apollo Research →