AI Research Intern

◈About the Role

Work with our research team on interpretability infrastructure, tooling that helps labs understand what their models are actually learning.

✓What You Will Do

• —Prototype experiments in PyTorch and JAX
• —Build internal tools for visualizing model internals
• —Co-author research notes with senior team members

◎Requirements

• —Strong Python; familiarity with at least one deep-learning framework
• —Coursework or independent projects in ML
• —Fluent English; comfortable reading and discussing papers

★Nice to Have

• —Open-source contributions or research artifacts
• —Interest in AI safety or interpretability research