Applied Researcher; Product

Final date to receive applications: We are conducting interviews actively and aim to fill this role as soon as we find someone suitable.

Join our new AGI safety product team and help transform complex AI research into practical tools that reduce risks from AI. As an applied researcher, you’ll work closely with our CEO (also Head of Product), product engineers and the Evals team software engineers to build tools that make AI agent safety accessible at scale for our customers. Our current focus is the monitoring of AI coding agents for AI safety and security failures.

You will join a small team and will have significant ability to shape the team & tech, and have the ability to earn responsibility quickly.

You will like this opportunity if you’re passionate about using empirical research to make AI systems safer in practice. You enjoy the challenge of translating theoretical AI risks into concrete detection mechanisms. You thrive on rapid iteration and learning from data. You want your research to directly impact real-world AI safety.

• 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
• Iterate on monitoring approaches based on empirical results, balancing detection accuracy with computational efficiency
• Stay current with research on AI safety, agent failures, and detection methodologies
• Stay current with research into coding security and safety vulnerabilities

• Develop a comprehensive library of monitoring prompts tailored to specific failure modes (e.g., security vulnerabilities, goal misalignment, deceptive behaviors)
• Experiment with different reasoning strategies and output formats to improve monitor reliability
• Design and test hierarchical monitoring architectures and ensemble approaches
• Optimize log pre-processing pipelines to extract relevant signals while minimizing latency and computational costs
• Implement and evaluate different scaffolding approaches for monitors, including chain-of-thought reasoning, structured outputs, and multi-step verification

• Fine-tune smaller open-source models to create efficient, specialized monitors for high-volume production environments
• Design and build agentic monitoring systems that autonomously investigate logs to identify both known and novel failure modes

• 2+ years of experience conducting empirical research with large language models or AI systems
• Strong experience with AI coding agents. For example, having extensively used and compared frontier coding agents. For example, having designed / developed coding agents
• Experience with LLM-as-a-judge setups
• Experience designing and running experiments, analyzing results, and iterating based on empirical findings (e.g., prompting, scaffolding, agent design, fine-tuning, or RL).
• Strong Python programming skills
• Demonstrated ability to work independently on open-ended research problems

• Experience with AI evaluation frameworks, in particular Inspect (though other frameworks are relevant as well)
• Familiarity with AI safety concepts, particularly agent-related risks
• Familiarity with computer security, e.g. security testing and secure system design
• Experience fine-tuning language models or working with smaller open-source models
• Previous work building developer tools or monitoring systems
• Publications or contributions to AI safety or ML research
• Experience with production log systems or production log analysis

We want to emphasize that people who feel they don’t fulfill all of these characteristics but think they would be a good fit for the position nonetheless are strongly encouraged to apply. We believe that excellent candidates can come from a variety of backgrounds and are excited to give you opportunities to shine.

• Build a comprehensive failure mode database
  :
  Systematically collect and categorize 100+ distinct AI agent failure modes across safety and security dimensions, creating the foundation for our monitoring library.
• Develop and validate monitoring approaches
  :
  Create and empirically test monitoring prompts and strategies for key failure categories, establishing clear metrics for monitor performance and building evaluation frameworks to track progress.
• Optimize the monitoring pipeline
  :
  Improve log preprocessing and monitor scaffolding to achieve measurable improvements in detection accuracy, false positive rates, and computational efficiency.
• Advance monitoring capabilities
  :
  Begin work on advanced approaches such as fine-tuned specialized monitors or agentic investigation systems, moving our monitoring from reactive detection toward proactive risk…