Publisher
source

Hanqi Yan

Just Landed

New Today

Postdoctoral Researcher in LLM Interpretability and Safety King's College London in United Kingdom

Degree Level

Postdoc

Field of study

Computer Science

Funding

No salary, stipend, or other funding details are provided. The position is a 2-year fixed-term postdoctoral appointment.

Country flag

Country

United Kingdom

University

King's College London

Apply for this position

Free with an ApplyKite account: the application link, the deadline in your tracker and a check of your fit.

Keywords

Computer Science
Artificial Intelligence
Natural Language Processing
Interpretability
Large Language Models

More like this

Suggested positions

Publisher
source

Technische Universität Dresden

Country flag

Germany

ScaDS.AI Dresden/Leipzig is offering two Research Associate/Postdoctoral positions in Dresden within the research project “Neuro-Symbolic AI with Logic-Memory Decomposition” (Neuro-SAIL) . The project investigates verifiable neuro-symbolic artificial intelligence architectures. The research may focus on Natural Language Processing , Large Language Models , Knowledge Graphs , or related areas such as Graph Machine Learning . The work is assigned to the Chair of Scalable Software Architectures for...

Computer Science
Natural Language Processing
Large Language Models

2 days ago

Publisher
source

University of Oxford

Country flag

United Kingdom

University of Oxford is advertising a three-year, full-time postdoctoral role in LLMs / mechanistic interpretability with a distinctive interdisciplinary focus on theology and science and religion . The position sits in the Ian Ramsey Centre for Science and Religion , part of the Faculty of Theology and Religion, with offices in the Schwarzman Centre for the Humanities. The project is called God and the Machine and is funded by the John Templeton Foundation . The post is aimed at someone who wan...

Computer Science
Philosophy
Religious Studies
+3 more

1 month ago

Publisher
source

University of Oxford

Country flag

United Kingdom

SOFAIR (Science of Fundamental AI Research Lab) is recruiting senior postdoctoral researchers to help shape the future of open artificial intelligence. The positions focus on fundamental AI research within a collaborative research environment. The postdoctoral researchers will work with researchers from University College London, the University of Oxford, the University of Cambridge and the University of Edinburgh. The lab is connected with the OATML Group at the University of Oxford, led by Pri...

Computer Science
Artificial Intelligence
ML

4 days ago

Publisher
source

Marco Valentino

University of Sheffield

Country flag

United Kingdom

Fully funded PhD opportunity at the University of Sheffield in Neurosymbolic World Models for Robotic Manipulation , starting in October 2027 . This multidisciplinary project spans the School of Computer Science , the School of Electrical and Electronic Engineering , the Centre for Machine Intelligence , Sheffield NLP , and Sheffield Robotics . The topic sits at the intersection of Computer Science , Robotics , Electrical Engineering , and Artificial Intelligence , with a strong focus on neurosy...

Computer Science
Electrical Engineering
Information Technology
+4 more

1 month ago

Publisher
source

Rashid Kamal

University of Ulster

Country flag

United Kingdom

Fully funded PhD opportunity at Ulster University in Secure & Trustworthy AI-Generated Software (SAFE-GEN). This project sits at the intersection of Computer Science , Software Engineering , Cybersecurity , Artificial Intelligence , Machine Learning , and Explainable AI (XAI) . The research investigates vulnerabilities introduced by LLM coding assistants and aims to develop intelligent, language-agnostic methods to detect, localise, and explain security weaknesses in both human-written and AI-ge...

Computer Science
Artificial Intelligence
Cybersecurity
+4 more

3 weeks ago

About this position

King's College London is recruiting a Postdoctoral Researcher in LLM Interpretability and Safety for a two-year project on understanding and mitigating undesirable behaviours in large language models.

The research will address mechanistic interpretability, reward hacking, and misalignment in LLMs. The project aims to improve understanding of how these systems behave and contribute to the development of safer and more trustworthy artificial intelligence.

The successful researcher will work in the research environment at King's College London under the leadership of Assistant Professor Hanqi Yan, contributing to research at the intersection of natural language processing, large language models, interpretability, and AI safety.

Funding details

No salary, stipend, or other funding details are provided. The position is a 2-year fixed-term postdoctoral appointment.

What's required

Applicants must hold a PhD in NLP, AI, LLMs, or a related field and have a strong research track record.

How to apply

Email your CV and research statement to [email protected]. Use the subject line “[KCL-AISafety-Postdoc] Your Name.” Contact Hanqi Yan with questions about the position.

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts and confirm requirements with the university.

Professors

Assistant Professor

University Name
Country flag

United Kingdom

Research Interests

Artificial Intelligence

Interpretability

Natural Language Processing

Computer Science

Large Language Models