Safety Research Scholar Intern

Scale AI; United States; Remote; USD 114,000 - 162,000; Full time

Benefits offered by this job

Mentorship from Scale Labs researchers

Internship extension opportunities

Job summary

New Grad is seeking Research Scholars for a remote internship in the United States to tackle empirical AI safety questions. You will work with a Scale Labs mentor to turn safety questions into experiments, build evaluation tools, and document reproducible results.

Applicants should be pursuing or have completed a PhD in CS, ML, statistics, or mathematics and be able to work with high-level guidance, communicate findings clearly, and collaborate across teams.

Qualifications

• PhD in CS, ML, statistics, mathematics, or a related field.
• Experience communicating research clearly and handling confidential information.
• Ability to work with high-level guidance and propose experiments.

Responsibilities

• Owns research end to end: turn safety questions into hypotheses and experiments.
• Build evaluation harnesses, environments, datasets, and analysis tooling.
• Identify confounds and interpret results to inform next steps.
• Produce reproducible code, experiment logs, and precise technical writing.

Skills

Strong communication

Research planning

Critical thinking

Collaborative skills

Education

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

Tools

Python

Git

Job description

About the Program

The 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

Mentors will guide Research Scholars on projects in selected AI safety research areas in select AI safety research areas, such as:

• 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 the Human 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’ll 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 ensuring the safe and responsible development of 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 the Role

• Location: Remote within the United States, including California and New York
• Hours: 20 hours per week
• Term: 3 months, with the option to extend to 6–12 months for exceptional candidates (part‑time Internship structure)
• Compensation: $100/hour

PLEASE NOTE: Our policy requires a 90-day waiting period before reconsidering candidates for the same role. This allows us to ensure a fair and thorough evaluation of all applicants.

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 appropriate and necessary to manage applicants’ needs, provide our services, and comply with applicable laws. Any information we collect in connection with your application will be treated in accordance with our internal policies and programs designed to protect personal data. Please see our privacy policy for additional information.