AI Vulnerability Expert - Fully Remote

As an AI Vulnerability Expert, you will probe models to identify weaknesses and design challenges to test their capabilities. You will work as a team to share insights and improve the benchmark. This role requires a strong background in STEM, experience in research and security, and proficiency in Python and Git.

What You Will Do

Your main responsibilities will be to probe models to explore how they handle coding, ML, and analysis tasks, identify spots where models quietly fail, design challenges to test their capabilities, and document findings clearly with reproducible evidence and steps.

Why It Might Be a Fit

This role is a good fit for someone with a strong background in STEM, experience in research and security, and proficiency in Python and Git. You will have the opportunity to work as a team to share insights and improve the benchmark, and you will be able to engage reliably for approximately 35 hours/week.

Requirements

• MSc or PhD in a STEM field or equivalent practical experience
• 1+ years of experience in research, research-engineering, security, or AI-evaluation roles
• Ability to identify vulnerabilities, edge cases, or failure modes in LLMs or ML systems
• Proficiency in Python and Git for scripting probes and analyses
• Familiarity with LLM capabilities, limitations, and evaluation techniques