# Research Scientist, Interpretability

Hiring organization: [Menlo Ventures Portfolio](https://career.thegoodapps.co/organizations/menlo-ventures-portfolio)

Canonical page: https://career.thegoodapps.co/jobs/f777db9a-212b-4cca-bd31-739d5cb2694e

Listed on Menlo Ventures Portfolio's own careers site. Applications go to them directly.

- Employment type: full time
- Location: San Francisco, CA
- Salary: 350000 – 850000 USD per year

## Summary

This role involves developing methods to understand how large language models work by analyzing their learned algorithms and building interpretability tools. It suits researchers with a strong scientific background who want to contribute to AI safety through mechanistic understanding and enjoy collaborative, experimental science.

_Our summary, not Menlo Ventures Portfolio's wording._

## Skills named

Python

## Required

- Strong track record of scientific research
- Experience or demonstrated work in interpretability
- Python proficiency
- Ability to design and run experiments
- Comfortable with collaborative team science

## Nice to have

- Experience with large language models
- Background in AI safety or alignment research
- Published interpretability work
- Experience with neural network visualization and analysis

Apply on Menlo Ventures Portfolio's site: https://job-boards.greenhouse.io/anthropic/jobs/4980427008