Artificial Intelligence Researcher | Remote

About the role

We are seeking an Artificial Intelligence Researcher to join our team remotely. This position focuses on analyzing advanced AI models to uncover weaknesses and enhance their performance. The ideal candidate will engage in collaborative efforts to refine evaluation benchmarks and share findings with fellow researchers.

Key facts

What you'll do

• Investigate leading AI models to discover vulnerabilities and their potential failure points.
• Create complex tasks aimed at revealing model deficiencies.
• Record and present findings with clear and reproducible evidence.
• Work with task creators to improve benchmark challenges.
• Communicate insights with researchers to enhance evaluation benchmarks.

Requirements

• Master's degree or PhD in a STEM discipline, or equivalent hands-on experience.
• Significant experience in research, security, or roles focused on AI evaluation.
• Proven track record of identifying vulnerabilities in large language models or machine learning systems.
• Strong skills in Python and Git for scripting and analysis purposes.
• Understanding of the capabilities, limitations, and assessment methods for large language models.

Nice to have

• Not specified

Skills & tools

• Python
• Git

Practical notes

• To apply, please use the Easy Apply feature.
• Applications will be assessed based on the specified requirements.
• Candidates who qualify will receive an email detailing the next steps in the application process.
• Follow the instructions in the email to complete your application.