← Back to all jobs

Transluce logo

Research Engineer, Scalable Interpretability

Transluce

Job AI safety & policy

Where
On-site: On-site · San Francisco, CA · USA
Level
Early–Mid career, 1–9 yrs
Pay
$250k–$500k, top of range above $100k a year$250,000 – $500,000
Apply by
Rollingposted 10 Jun
Hours and type
Full-time
Kind of work
Technical & Engineering
Added to CFI
22 August 2026Posted by employer 10 June 2026
Network
LinkedIn

About the role

Develop and train scalable oversight assistants that detect unexpected behaviours in AI systems, including building evaluations and scaling training pipelines up to 1T-parameter models. Works in person in San Francisco.

Summary of the employer's page written by AI. Check the full listing before you apply.

Requires

Experience fine-tuning language models and creating evaluations; strong programming

Apply on employer site