RemoteLeaf Logo
Log in Sign up

Safety Research Scholar - Human Frontier Labs

4 hours, 38 minutes ago
United States
Internship
Mid Level
AI (Artificial Intelligence)
Artificial Intelligence and Machine Learning
Machine Learning
Apply Now
Scale AI

Scale AI

Scale AI accelerates AI application development with high-quality training data for industries like self-driving cars, AR/VR, and robotics, enabling ML teams to build advanced models efficiently.

Diversified Consumer Services
501-1000
Founded 2016
$603M raised
View All Jobs 2

Description

  • Own an AI safety research project from high-level question through hypotheses, baselines, controlled experiments, and next-step decisions.
  • Develop research on areas such as AI control, alignment evaluations, multi-agent safety, recursive self-improvement safety, evaluation science, or misuse risk.
  • Implement and debug evaluation harnesses, agent environments, datasets, monitoring methods, or post-training experiments.
  • Meet weekly with a Scale researcher to align on research direction and incorporate feedback.
  • Identify experimental confounds and distinguish model capabilities from behavioral tendencies.
  • Interpret positive and negative results and propose follow-up experiments with limited day-to-day direction.
  • Create reproducible code, experiment logs, analyses, and precise technical documentation.
  • Produce research papers for potential submission to leading ML conferences, subject to research, security, and communications review.

Requirements

  • Motivation to support the safe and responsible development of advanced AI systems.
  • Interest in technical AI safety research, including alignment evaluations, AI control, monitoring, multi-agent safety, or open-weight model safety.
  • Pursuing or completed PhD in computer science, machine learning, statistics, mathematics, or a related field; equivalent research track record considered.
  • Ability to make progress with high-level guidance, including implementing, debugging, interpreting results, and proposing experiments.
  • Strong research communication skills and ability to document work clearly.
  • Ability to handle confidential information and internal systems responsibly.
  • Availability to work remotely within the United States, including California and New York.
  • Availability for 20 hours per week for an initial 3-month term.
  • Applicants must submit a resume or CV, Google Scholar profile if available, and an example of a substantially owned research project with a brief contribution summary.

Benefits

  • Compensation of $100 per hour.
  • Remote work within the United States.
  • Part-time schedule of 20 hours per week.
  • Initial 3-month term with potential extension to 6–12 months for exceptional candidates.
  • Mentorship and weekly guidance from a Scale researcher.
  • Reasonable accommodations for applicants with physical or mental disabilities.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Redhorse

AI/ML Modeling Team Lead

Redhorse 201-500 Aerospace & Defense

Redhorse Corporation is seeking an AI/ML Modeling Lead to guide predictive maintenance modeling for the U.S. Air Force CBM+ program, improving aircraft availability and reducing operational downtime.

United States Full-time Lead AI (Artificial Intelligence)
$140k-$170k
Agile Feature Engineering Git Kanban Machine Learning Power BI Scrum Tableau
4 hours, 23 minutes ago
CrowdGen by Appen

[Vietnamese - Japan] - Voice Recording Specialist

CrowdGen by Appen Internet Software & Services

Join Appen as an independent contractor on Project Morava, recording Vietnamese scripted voice prompts in Japan to help train and evaluate voice AI systems.

Japan Contract Entry Level AI (Artificial Intelligence)
$0k-$0k
4 hours, 23 minutes ago
CrowdGen by Appen

[Russian - Latvia] - Voice Recording Specialist

CrowdGen by Appen Internet Software & Services

As an Independent Contractor on Appen’s Project Morava, you will record scripted Russian voice prompts via smartphone to help train and evaluate voice AI systems.

Latvia Contract Entry Level AI (Artificial Intelligence)
$0k-$0k
4 hours, 23 minutes ago
CrowdGen by Appen

[Russian - Estonia] - Voice Recording Specialist

CrowdGen by Appen Internet Software & Services

As an independent contractor on Appen’s Project Morava, record scripted Russian voice prompts via smartphone to support the training and evaluation of voice AI systems.

Estonia Contract Entry Level AI (Artificial Intelligence)
$0k-$0k
4 hours, 23 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers