Join a dynamic team of Software Engineers to develop cutting-edge evaluation systems for AI security, impacting government understanding of AI capabilities and safety standards.
Join a team of cybersecurity experts to evaluate frontier AI models, design cyber ranges, and contribute to the understanding of AI cyber capabilities with real-world impact.
Join the Alignment Red Team as a Research Engineer or Research Scientist, focusing on evaluating and mitigating misalignment risks in frontier AI systems through innovative research and software development.
The Research Engineer will focus on developing scalable solutions in LLM post-training and fine-tuning, particularly using Reinforcement Learning, to mitigate AI risks related to human influence.
The Engineering Lead will manage a team focused on developing evaluations, building data pipelines, and conducting complex research studies on AI's influence on human behavior.
Research Scientists and Engineers in the Misuse Red Team will develop and analyze attacks and protections for large language model systems, contributing to impactful AI security research.
Join the Control Red Team to research and evaluate AI control measures, designing experiments and assessing real-world risks to enhance AI safety.
Design and build reliable systems as a Senior Software Engineer in the Chem-Bio team, enabling researchers to run experiments and ship results quickly.
Join the AI Security Institute's Core Technology Team as a Software Engineer, working on impactful research-oriented software and infrastructure with cutting-edge technologies.
Page 1 ยท 9 results
