Safety Research Scholar (AI Safety)

Location: Canada, the United Kingdom, or the United States

Company

hirify.global develops reliable AI systems, high-quality training data, and full-stack technologies for AI applications used by enterprises and governments.

What you will do

• Own an AI safety research project from research question through hypotheses, baselines, controlled experiments, and conclusions.
• Build and debug evaluation harnesses, agent environments, datasets, monitoring methods, and post-training experiments.
• Investigate alignment evaluations, AI control, chain-of-thought monitoring, multi-agent safety, recursive self-improvement safety, and misuse risks.
• Identify confounds, interpret negative results, distinguish capability from behavioral propensity, and select follow-up experiments.
• Produce reproducible code, experiment logs, technical analyses, and research papers for submission to leading ML conferences.
• Work with a hirify.global researcher through weekly mentoring and feedback while driving day-to-day research independently.

Requirements

• Motivation to reduce catastrophic risks from advanced AI systems.
• Interest in technical AI safety research, including alignment evaluations, AI control, monitoring, multi-agent safety, or open-weight model safety.
• PhD in computer science, machine learning, statistics, mathematics, or a related field, or an equivalent research track record.
• Ability to make progress with high-level guidance, including implementing, debugging, interpreting results, and proposing next experiments.
• Clear research communication and responsible handling of confidential information and internal systems.
• Work authorization and security requirements must be completed during onboarding.

Culture & Benefits

• Work alongside AI safety researchers on consequential problems in frontier AI.
• Receive weekly mentorship while owning a substantial part of a research project.
• Research outputs may include papers submitted to NeurIPS, ICML, and ICLR.
• Inclusive and equal-opportunity workplace with reasonable accommodation support.

Hiring process

• Submit a resume or CV, Google Scholar profile if available, and a substantially owned research project with a brief contribution summary.
• Discuss a previous research project, including unsuccessful approaches and lessons learned.
• Complete a research-design exercise and applicable recruiting, work-authorization, security, and onboarding steps.
• A 90-day waiting period applies before reconsideration for the same role.