Safety Research Scholar - Human Frontier Labs

Scaleai; Canada; On-site; CAD 90,000 - 130,000; Full time

Job summary

Scale AI invites researchers to join the Human Frontier Collective in Canada, a collaboration with Scale Labs to build a cohort focused on empirical AI safety foundations. Scholars tackle how models fail, safety controls under pressure, and long-horizon behaviors, mentored through the project lifecycle.

You'll own projects end to end, develop measurement harnesses and experiments, and present reproducible code and papers to top ML conferences.

Qualifications

• PhD in CS/ML/Statistics/Mathematics or related field.
• Ability to progress with high-level guidance and implement/debug.
• Strong written and verbal communication; handle confidential information.

Responsibilities

• Own research end to end: from question formulation to experiments and publication.
• Build evaluation harnesses, agent environments, datasets and monitoring.
• Produce reproducible code, experiment logs, and precise technical writing.

Skills

Research

Education

PhD in CS/ML/Statistics/Mathematics or related field

Job description

About the ProgramThe Human Frontier Collective (HFC)

brings researchers and scientists together to tackle consequential problems in AI. In partnership with Scale Labs, we are building a small cohort of researchers to work on the empirical foundations of AI safety.

That work includes finding where models fail, checking whether safety controls hold up under pressure in realistic settings, and studying how AI agents (mis-)behave over long-horizon tasks. Scholars take open research questions like these and turn them into work that improves how frontier AI systems are evaluated and safeguarded.

Each scholar owns a substantial part of a safety research project. You'll work alongside a mentor from the research question through the experiments to deciding what to test next.

Research Areas

• AI control and chain-of-thought monitoring: Developing techniques to oversee and constrain AIs, including detecting harmful intent or deception.

• Alignment auditing and evaluations: Building scalable methods to test whether models have hidden goals, misaligned behaviors or unsafe tendencies.

• Multi-agent safety: Studying the risks that emerge when multiple agents interact, such as collusion, coordinated failures, or unexpected collective behavior.

• Recursive Self-Improvement (RSI) safety: Investigating how to keep AI systems safe and aligned as AIs increasingly contribute to their own development.

• Science of Evaluations: examining when and how models recognize they're being tested, and how situational awareness affects the reliability/validity of evaluations.

• Misuse risks and evaluations: Developing methods to assess how AI systems could be exploited by malicious actors, including evaluating their potential to enable harmful activities.

Projects are matched to demonstrated expertise; we don't expect any candidate to cover every area.

Representative Research

• ASPI: 728 task-attack scenarios testing how clarification-seeking changes prompt-injection vulnerability in LLM agents.

• PropensityBench: simulating real-world pressure to choose between safe or harmful behavior

• BioRiskEval: evaluating whether safeguards for open-weight bio-foundation models remain robust under fine-tuning and probing.

• See more work from theHuman Frontier Collective.

What You'll Do

Projects are mentor-guided. By default, you will be given a list of research proposals and match you with one based on your research interests and background. You will meet weekly with a Scale researcher who sets the direction and gives feedback, and you will drive the day-to-day work.

• Own research end to end: Turn a high-level safety question into hypotheses, baselines, and controlled experiments, and produce work that others can inspect and build on.

• Build the measurement: Implement and debug evaluation harnesses, agent environments, datasets, monitoring methods, or post-training experiments.

• Exercise research judgment: Identify confounds, separate what a model can do from what it tends to do, make sense of negative results, and decide what to try next without step-by-step direction.

• Make the work legible: Produce reproducible code, experiment logs, analysis, and precise technical writing. External outputs, where appropriate, remain subject to research, security, and communications review. Outputs also include research papers, which will be submitted to top ML conferences (NeurIPS, ICML, ICLR).

Who We're Looking For

You may be a good fit if you:

• are motivated by reducing catastrophic risks from advanced AI systems;

• are interested in technical safety research, such as alignment evaluations, AI control, monitoring, multi-agent safety, or open-weight model safety;

• are pursuing or have completed a PhD in CS, ML, statistics, mathematics, or a related field (we also encourage researchers with an equivalent track record to apply);

• can make progress with high-level guidance, including implementing, debugging, getting unstuck, interpreting results, and proposing next experiments;

• communicate research clearly and handle confidential information and internal systems responsibly.

About Us:

*At Scale, our mission is to develop reliable AI systems for the world's most important decisions. Our products provide the high-quality data and full-stack technologies that power the world's leading models, and help enterprises and governments build, deploy, and oversee AI applications that deliver real impact. We work closely with industry leaders like Meta, Ernst& Young, Mayo Clinic, Time Inc., the Government of Qatar, and U.S. government agencies including the Army and Air Force. We are expanding our team to accelerate the development of AI applications.

*We believe that everyone should be able to bring their whole selves to work, which is why we are proud to be an inclusive and equal opportunity workplace. We are committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability status, gender identity or Veteran status.

*We are committed to working with and providing reasonable accommodations to applicants with physical and mental disabilities. If you need assistance and/or a reasonable accommodation in the application or recruiting process due to a disability, please contact us at [e-mail]. Please see the United States Department of Labor's Know Your Rights poster for additional information.

*We comply with the United States Department of Labor's Pay Transparency provision.

*PLEASE NOTE: We collect, retain and use personal data for our professional business purposes, including notifying you of job opportunities that may be of interest and sharing with our affiliates. We limit the personal data we collect to that which we believe is appropriat