Applied Researcher (Monitoring)

TL;DR

Applied Researcher (Monitoring): Building and optimizing tools for AI agent safety monitoring with an accent on systematically collecting and cataloging failure modes, designing experiments, and developing comprehensive monitoring prompts. Focus on translating theoretical AI risks into concrete detection mechanisms and iterating on monitoring approaches based on empirical results.

Company

hirify.global is a company focused on transforming complex AI research into practical tools that reduce risks from AI.

What you will do

• Systematically collect and catalog coding agent failure modes from various sources.
• 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.
• Optimize log pre-processing pipelines to extract relevant signals while minimizing latency.
• Stay current with research on AI safety, agent failures, detection methodologies, and coding security vulnerabilities.

Requirements

• Passion for using empirical research to make AI systems safer in practice.
• Enjoy the challenge of translating theoretical AI risks into concrete detection mechanisms.
• Thrive on rapid iteration and learning from data.
• Desire for research to directly impact real-world AI safety.
• English: B2 required.

Nice to have

• Experience fine-tuning smaller open-source models for efficient, specialized monitors.
• Ability to design and build agentic monitoring systems that autonomously investigate logs.

Culture & Benefits

• Join a new AGI safety monitoring team.
• Work closely with the CEO, monitoring engineers, and Evals team software engineers.
• Significant ability to shape the team and tech.
• Opportunity to earn responsibility quickly.

Hiring process

• Rolling application review.
• Applications accepted until January 16, 2026.