Applied Researcher (Product)

Core responsibilities:

• Systematically collect and catalog coding agent failure modes from real-world instances, public examples, research literature, and theoretical predictions
• Design and conduct experiments to test monitor effectiveness across different failure modes and agent behaviors
• Build and maintain evaluation frameworks to measure progress on monitoring capabilities
• Develop a comprehensive library of monitoring prompts tailored to specific failure modes (e.g., security vulnerabilities, goal misalignment, deceptive behaviors)

This role helps transform complex AI research into practical tools that reduce risks from AI, making AI agent safety accessible at scale for customers and directly impacting real-world AI safety.

Required skills and qualifications:

• Passion for using empirical research to make AI systems safer in practice
• Ability to translate theoretical AI risks into concrete detection mechanisms
• Experience with rapid iteration and learning from data
• Knowledge of AI safety, agent failures, and detection methodologies

No specific benefits, compensation, or salary information mentioned in the posting.

Apollo Research is primarily concerned with risks from Loss of Control in AI systems, particularly deceptive alignment/scheming, and works on detection, science, and mitigations of these risks while developing tools to prevent harms from widely deployed AI systems.