San Francisco · Palo Alto$200k – $330k+ equity
Founding Member of Technical Staff
The role
Develop white-box auditing methods for frontier AI, including interpretability tools, robustness experiments and benchmarks of model beliefs, goals and plans. London is preferred; remote candidates in Europe/UK must travel regularly to London. Full-time, initially two years subject to funding. The employer advertises two openings under this single role and $100,000–$135,000 gross annual base salary plus a separate 5% end-of-year bonus. Apply by September 27, 2026. A PhD is not required if equivalent research ability can be demonstrated.
Published by Parallax on their own careers page and reproduced here unedited. Read it at Parallax.
Apply at Parallax → Applications go directly to Parallax. This board does not sit in between, take a fee from you, or see your application.
Free. One email on Thursdays.
More roles like this
Matched by discipline, title, listed location and work arrangement.
Same discipline: Alignment & Interpretability · Both have staff / lead titles
Cambridge, United Kingdom
Same discipline: Alignment & Interpretability · Both have staff / lead titles
Paris, France · London, United Kingdom
Same discipline: Alignment & Interpretability · Both have staff / lead titles · Shared listed location
San Francisco, CA · London +1
Same discipline: Alignment & Interpretability · Both have staff / lead titles
Palo Alto, CA$180k – $440k
Same discipline: Alignment & Interpretability · Both have staff / lead titles