Senior Researcher: AI Interpretability & Safety

University of Oxford, Department of Engineering Science; Oxford; On-site; GBP 49,000 - 58,000; Full time

Job summary

The Department of Engineering Science at the University of Oxford in central Oxford seeks a full-time Senior Researcher to join the Technical AI Governance programme. The post is fixed-term to 1 year, with the possibility of an extension for a further year, and is funded by the Oxford Martin AI Governance Initiative.

You will work on Interpretability, evaluations and AI safety for continuously learning systems, evaluating moving behaviours and tracking whether safety properties hold under

Qualifications

• PhD in machine learning, computer science, or a closely related field with several years of research experience.
• Publications in top venues (NeurIPS, ICML, ICLR, ACL, EMNLP) or AI safety venues.
• Experience in interpretability, model evaluation/benchmarking, continual/lifelong learning, or AI safety.

Responsibilities

• Work on interpretability, evaluations and AI safety for continuously learning systems.
• Evaluate systems whose behaviour changes over time and assess whether safety properties hold under change.

Skills

Strong publications

Experiment design

Interpretable AI

Research in AI safety

Education

PhD in ML/CS or related field

Job description

The Department of Engineering Science at the University of Oxford in central Oxford seeks a full-time Senior Researcher to join the Technical AI Governance programme. The post is fixed-term to 1 year, with the possibility of an extension for a further year, and is funded by the Oxford Martin AI Governance Initiative.

You will work on Interpretability, evaluations and AI safety for continuously learning systems, evaluating moving behaviours and tracking whether safety properties hold under