Research Scientist, Truthful AI

• In this role, you'll conduct technical AI research focused on improving the safety of large language models.
• Produce high-impact academic papers through experimental investigation of LLM behaviour.
• Work independently on research projects with guidance from experienced mentors.
• Develop insights into AI safety challenges related to LLM capabilities and alignment.
• Share research findings widely to advance the broader AI safety community.

• In this role, you'll conduct technical AI research focused on improving the safety of large language models.
• Produce high-impact academic papers through experimental investigation of LLM behaviour.
• Work independently on research projects with guidance from experienced mentors.
• Develop insights into AI safety challenges related to LLM capabilities and alignment.
• Share research findings widely to advance the broader AI safety community.

TruthfulAI is a nonprofit that researches situational awareness, deception, and hidden reasoning in language models.