Job Description

Postdoctoral Research Associate on Architectures for LLM-based agents

Full time, Fixed-term contract for 30 months, tenable immediately to end before 31 May 2028

Grade 07RS: 38,674-46,913 per annum inclusive of Oxford University weighting

Potential to under fill at grade 06RS: 34,982-40,855 per annum inclusive of Oxford University weighting

The Department of Computer Science seeks to employ a postdoctoral researcher to work on a new project in the area of LLMs/multi-agent systems, under the direction of PI Professor Michael Wooldridge. The post is a full-time, fixed term position, available for up to 30 months, tenable immediately, to conclude before May 31st 2028.

Intelligent agents have a venerable history in AI: since the 1980s the problem of how to build hardware and/or software agents that can autonomously act on our behalf in pursuit of delegated preferences has been studied continually, albeit mostly in the context of classic AI (symbolic reasoning and planning). Recently the concept of agents has come to the fore again, prompted by the rise of Large Language Models (LLMs) - put crudely, the idea is to use LLMs, in the sense of being powerful general purpose intelligent systems, as the "brains" of an agent.

We aim to revisit the question of agent design, where LLMs provide NLP interfaces and reasoning capabilities for agents. Our work will be informed by four decades of agent design in AI. We will design and build an LLM-agent platform and evaluate it in a demonstrator. Our work is expected to embrace emerging standards for LLM agents (notably MCP, A2A). Note that the successful candidate will work in collaboration with two other postdocs on a closely aligned project "Rethinking multi-agent systems in the era of LLMs", funded by the Schmidt Sciences Foundation, and also working under the supervision of Prof Wooldridge.

Candidates will be expected to have a PhD (or be close to completion) in a related area. The primary selection criteria will be relevant research experience, publication track record, and ability to contribute to the project.

What We Offer

As an employer, we genuinely care about our employees' wellbeing and this is reflected in the range of benefits that we offer including:

An excellent contributory pension scheme

38 days annual leave (pro-rata for part-time jobs)

A comprehensive range of childcare services

Family leave schemes

Cycle loan scheme

Discounted bus travel and Season Ticket travel loans

Membership to a variety of social and sports clubs

Diversity

Committed to equality and valuing diversity.

Application Process

You will be required to upload an up-to-date CV and a supporting statement as part of your online application.

Your supporting statement must clearly demonstrate how you meet each of the essential selection criteria listed in the job description. Applications that do not include a supporting statement or CV, or fail to address the criteria in sufficient detail, will not be considered.

While we recognise the value of AI tools in assisting with application preparation, submissions that are

clearly AI-generated without personalisation or insight

will be rejected. It's crucial that your application reflects your own experiences and understanding of the role.

The closing date for applications is noon on 15th September 2025.

Interviews are expected to be
held in September