Research Scientist (Control)

Apollo Research is building AI safety products that translate control research into practical tools for reducing risks from AI. The Research Scientist (Control) will design and implement control protocols, conduct empirical experiments, develop monitoring systems and evaluation frameworks, and fine-tune models for detecting coding-agent failures in production environments.

Responsibilities:

• 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
• Build and maintain high-quality datasets to train and test monitors on
• Iterate on monitoring approaches based on empirical results, balancing detection accuracy with computational efficiency
• Contribute newly discovered coding agent failure modes to Apollo's shared failure mode library (owned by the AI Security & Control Researcher/Engineer) as they surface during monitor design, evaluation, and iteration
• Stay current with research on AI safety, agent failures, and detection methodologies
• Stay current with research into coding security and safety vulnerabilities
• Fine-tune open-source models to create efficient monitors for high-volume production environments
• Design and build agentic monitoring systems that autonomously investigate logs to identify both known and novel failure modes
• Incorporate adversarial findings from red-teaming campaigns into monitor design and evaluation, closing the loop between attack and defense