Job Summary
This role involves leading the research agenda focused on AI agent behavior and conducting experiments to identify potential failures of agents in production environments. The successful candidate will also be tasked with creating evaluation methods, designing new detection prototypes, and disseminating research findings through publications and blog content.
Responsibilities
- Establish and oversee the research strategy on AI agent behavior.
- Conduct experiments to analyze the failure modes of agents in real-world applications.
- Develop innovative evaluation frameworks for assessing AI performance.
- Prototype new methods for detecting anomalies in agent behavior.
- Publish research results in academic papers and share insights via blog posts.
Qualifications
- Extensive knowledge in interpretability, AI safety, or anomaly detection.
- Demonstrated strong communication abilities.
- Proven track record of designing and executing experiments.
- Experience in building and testing prototypes.
Raindrop provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.
