Senior Researcher — AI Interpretability & Safety

Corehr; Oxford; On-site; GBP 60,000 - 80,000; Full time

Job summary

University of Oxford in Oxford is seeking a Senior Researcher to join the Technical AI Governance programme within the Department of Engineering Science. The role focuses on interpretability, evaluations and AI safety for continuously learning systems, with a fixed-term of 1 year and potential extension.

The candidate will design and run large-scale experiments on foundation models, contribute to collaboration efforts, and engage with the university community to advance governance in AI systems.

Qualifications

• PhD in machine learning, computer science, or a closely related field.
• Strong publication record at NeurIPS, ICML, ICLR, ACL, EMNLP or AI safety venues.

Responsibilities

• Research on interpretability and AI safety for continually learning systems.
• Evaluate systems that adapt over time and assess whether safety properties hold under change.
• Collaborate with colleagues and contribute to the technical AI governance program.

Skills

Interpretability

AI Safety

Experimentation

Publications

Education

PhD in ML/CS

Job description

University of Oxford in Oxford is seeking a Senior Researcher to join the Technical AI Governance programme within the Department of Engineering Science. The role focuses on interpretability, evaluations and AI safety for continuously learning systems, with a fixed-term of 1 year and potential extension.

The candidate will design and run large-scale experiments on foundation models, contribute to collaboration efforts, and engage with the university community to advance governance in AI systems.