Postdoctoral Researcher, Explainable AINew
Lawrence Livermore National Laboratory
Job AI safety & policy
- Where
- Hybrid: Hybrid · Livermore, CA · USAHybrid, Livermore, CA
- Level
- Mid career, 5–9 yrsMid5–9 yrs
- Pay
- $143k, top of range above $100k a year$143,328 award
- Apply by
- Rollingposted 24 Sep
- Hours and type
- Full-time
- Kind of work
- Research
- Added to CFI
- 24 September 2026
- Network
About the role
Researches how AI models represent knowledge internally, using sparse decompositions, concept extraction and causal intervention, and builds interfaces for domain experts to inspect them. Works in LLNL's Machine Intelligence Group on national security science problems.
Summary of the employer's page written by AI. Check the full listing before you apply.
Requires
Recent PhD in computer science, ML, statistics or related field; deep learning research experience
This role's deadline has passed, so it is no longer on the board. See open roles.