Towards Next-Generation Trustworthy AI via Neuro-Symbolic Computing (Ref: CO/CZ-SF1/2026)

Job description

Artificial Intelligence (AI) is already an essential part of the world, from daily chatbots to assistants for education, healthcare, and software development.

However, current AI systems, including Large Language Models (LLMs) like ChatGPT, are prone to producing incorrect, inaccurate, or misleading outputs.

These failures can have serious consequences, such as misleading students, providing unsaf...e medical advice, or generating vulnerable code, fundamentally undermining the trustworthiness of AI.

The primary goal of this project is to address these critical challenges by developing a NeuroSymbolic AI framework.

The project aims to enhance the trustworthiness of AI systems by detecting untrustworthy training data, refining reasoning steps, and constraining outputs through rigorous mathematical methods called formal methods.

By integrating the learning capabilities of neural networks with the rigorous reasoning of formal methods, this project seeks to combine the strengths of both neural and symbolic architectures to create systems that are not only powerful but also verifiable and safe.

The project is supervised by Dr Chengyu Zhang (https://chengyuzhang.com/), an expert in Software Engineering, Programming Languages, Formal Methods, and Artificial Intelligence.

Dr Zhang has served on program committees for top-tier conferences (ICSE, FSE, ASE, ISSTA) and reviews for leading journals (TSE, TOSEM, TOPLAS, CUSR).

His research has been recognised with a PLDI Distinguished Paper Award and a Google Open Source Peer Bonus, and supported by an Amazon Research Award and a CCF-ANT Research Award.

This PhD project offers opportunities for global collaboration with researchers from prestigious institutions (including MIT, UCL, NUS, and ETH Zurich) and industry partners (such as AWS).

The work will directly contribute to the safety and reliability of AI in critical domains, aligning with the UK AI Opportunities Action Plan.

This self-funded PhD position is ideally suited for candidates who possess:

• Academic Background: A first-class or good 2:1 honours degree (or equivalent international qualification) in Computer Science, Software Engineering, Mathematics, or a closely related discipline.

• Technical Skills: Proven programming ability (e.g., Python, C/C++). Experience with machine learning, formal methods or theorem proving is a distinct advantage.

• Aptitude: Strong analytical, mathematical, and problem-solving skills, with a keen interest in developing robust and trustworthy AI systems.

• Communication: Excellent written and oral communication skills in English, essential for paper writing, presentations, and collaborations.

• Motivation: High level of self-motivation, a capacity for independent research, and a commitment to academic rigour.

The supervisor will provide weekly meetings, dedicated support for research and writing, and guidance on navigating the doctoral process.

Name of primary supervisor/CDT lead:

Chengyu Zhang c.zhang4@lboro.ac.uk

https://www.lboro.ac.uk/departments/compsci/staff/chengyu-zhang/

Entry requirements:

A first-class or good 2:1 honours degree (or equivalent international qualification) in Computer Science, Software Engineering, Mathematics, or a closely related discipline.

English language requirements:

Applicants must meet the minimum English language requirements.

Further details are available on the International website (http://www.lboro.ac.uk/international/applicants/english/).

Bench fees required: No

Closing date of advert: 30th June 2026

Start date: April 2026, July 2026, October 2026

Full-time/part-time availability: Full-time 3 years

Fee band: 2025/26 Band RB (UK £5,006, International £28,600)

How to apply:

All applications should be made online.

Under programme name, select Computer Science.

Please quote the advertised reference number: CO/CZ-SF1/2026 in your application.

To avoid delays in processing your application, please ensure that you submit a CV and the minimum supporting documents.

The following selection criteria will be used by academic schools to help them make a decision on your application.

Please note that this criteria is used for both funded and selffunded projects.

Please note, applications for this project are considered on an ongoing basis once submitted and the project may be withdrawn prior to the application deadline, if a suitable candidate is chosen for the project.

Project search terms:

artificial intelligence, computer science, software engineering, programming languages neuro-symbolic computing

Email Address Sci:

sci-pgr@lboro.ac.uk

Show full description

Choose what you’re giving feedback on

Report this listing