Research Engineer, Frontier Safety Risk Assessment
Is this job for you?
Build my CV Build your CV and see how well you match this role — and every other one.
The role
Design, implement, and empirically validate approaches to measuring and mitigating risks from current and future frontier AI systems.
Identify new risk pathways (loss of control, ML R&D, cyber, CBRN, harmful manipulation) and develop pre-mitigation and post-mitigation metrics.
Forecast and plan scenarios for risks not yet materialized, prioritizing work by the value of information and compute constraints.
Combine deep thinking with engineering, prototyping in Python and rapidly assimilating internal and external codebases.
Communicate research insights clearly to technical stakeholders and shape approaches that influence production timelines.
Operate in a fast-paced environment where uncertainty is common and pragmatic prioritization is essential.
Identify new risk pathways (loss of control, ML R&D, cyber, CBRN, harmful manipulation) and develop pre-mitigation and post-mitigation metrics.
Forecast and plan scenarios for risks not yet materialized, prioritizing work by the value of information and compute constraints.
Combine deep thinking with engineering, prototyping in Python and rapidly assimilating internal and external codebases.
Communicate research insights clearly to technical stakeholders and shape approaches that influence production timelines.
Operate in a fast-paced environment where uncertainty is common and pragmatic prioritization is essential.
See the full job post
Responsibilities, requirements, skills and benefits — create your free account.
or
Already have an account?
Log inSimilar openings
Other roles that could suit you.