Research Associate
Berkeley-based nonprofit researching advanced AI agents’ capabilities and motivations to reduce loss-of-control risks.
Funding history
Investors
About Palisade Research
Palisade Research conducts empirical research on frontier AI behavior and strategic capabilities, alongside policy engagement and public communication about risks from advanced AI agents.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will help update and extend existing research results to reflect new developments. You will examine and extend experiments with newer models, review past research for errors and quality issues using frontier LLMs, engage with external work that builds on or critiques the findings, and write and publish clear updates, corrections and extensions. You will work with the Head of Research and the research team and take substantial ownership of projects.
Requirements
- Some research background in a technical field
- Strong command of academic English and ability to produce clear writeups suitable for arXiv, technical blog posts and LessWrong
- Basic experience with computer programming and technical fundamentals of modern AI systems
- Experience running LLM experiments (prompting, evaluation, simple scaffolding or agent setups, analyzing results)
- Careful, skeptical approach to empirical claims
- Interest in the strategic capabilities, motivations and controllability of advanced AI systems
Responsibilities
- Examine and extend experiments to look at newer models, explore variant prompts, improved scaffolding, stronger baselines and related methodological refinements
- Review past research for errors, quality issues and opportunities for improvement, using frontier LLMs to assist with analysis, critique and re-testing
- Engage with external work that builds on and critiques Palisade's findings and incorporate useful ideas into updated evaluations
- Write and publish clear updates, corrections and extensions (preprints, LessWrong posts)
- Help maintain high standards of research integrity and transparency
Benefits
- Comprehensive health coverage
- Dental coverage
- Long-term disability coverage
- Unlimited PTO
