Join Parsed as a Founding Research Engineer to develop innovative AI solutions for healthcare.

Research Scientist, Interpretability - Remote

Anthropic

22 weeks ago

Anthropic

Mechanistic Interpretability

Reverse Engineering

Large Language Models (LLMs)

Python

Join Anthropic's Interpretability team to advance the understanding of AI systems through mechanistic interpretability.

Research Engineer, Interpretability - Remote

Anthropic

22 weeks ago

Anthropic

Python

Rust

GO

Java

Join Anthropic's Interpretability team to work on mechanistic interpretability of AI models, ensuring their safety and reliability.