ForGood
Home / Jobs /Research & Evaluation / Research Scientist
CF
Center for AI Safety (CAIS)

Research Scientist

LevelMid
Posted1d ago
Research & Evaluation

Quick answer

The Center for AI Safety is hiring a Research Scientist to conduct high-impact, empirical experiments aimed at improving the safety and reliability of frontier AI systems.

Role
Research Scientist
Organization
Center for AI Safety (CAIS)
Level
Mid
Category
Research & Evaluation

The role

The Center for AI Safety is seeking a Research Scientist to lead high-impact research aimed at mitigating societal-scale risks from frontier AI systems. This role involves designing and executing experiments on large language models, building evaluation benchmarks, and collaborating on publishable research. Candidates will work with dedicated compute clusters to focus on areas such as AI robustness, transparency, and model honesty. The position emphasizes empirical research and contribution to top-tier machine learning conferences.

What you'll do

  • Design and execute end-to-end research experiments on frontier AI models.
  • Train and fine-tune large transformer models using distributed infrastructure.
  • Develop and maintain comprehensive datasets and performance benchmarks.
  • Author and publish research findings in top-tier machine learning conferences.
  • Collaborate with internal and external partners to advance safety research.

What it takes

  • Current PhD student or experienced researcher in machine learning.
  • Strong publication record at top ML venues like NeurIPS, ICML, or ICLR.
  • Proven track record of empirical research in AI safety-relevant domains.
  • Proficiency with ML frameworks such as PyTorch.
  • Ability to independently launch, manage, and debug complex ML experiments.

What you'll bring

Machine LearningLarge Language Models (LLMs)PyTorchDistributed TrainingEmpirical ResearchAI Safety Benchmarking

Frequently asked questions

What is the primary focus of the Research Scientist role?

The role focuses on mitigating societal-scale risks from AI by conducting empirical research on frontier AI systems, including model robustness, transparency, and honesty.

What kind of academic or research background is required?

The organization prefers candidates who are current PhD students or researchers with a strong track record of empirical research and peer-reviewed publications at top ML conferences.

Is remote work supported for this position?

The job description does not explicitly specify the work location or remote status; interested candidates should contact the organization for clarification.

How should I apply for this position?

The posting does not provide a specific deadline or external application link, but interested applicants or those with referrals should follow the instructions provided on the CAIS website or reach out via their contact email.

How to apply

Apply directly on Center for AI Safety (CAIS)'s site. We link straight through — no resume parsing, no profile to fill out.

Apply now →

This listing is aggregated from a third-party source and its summary may be auto-generated, so details can be inaccurate or out of date. ForGood is not the employer and is not liable for the content — please verify everything on Center for AI Safety (CAIS)'s official posting before applying.