Grade UE07: £41,064‑£48,822 per annum
College of Science and Engineering, School of Informatics
Fixed Term: 13 months
Full Time: 35 hours per week
The Opportunity
The position is in collaboration with the Huawei Trustworthy Technology and Engineering Laboratory Munich (TTE-DE). As part of this project, we aim to create a new generation of large language model (LLM) agents that are more reliable, consistent and trustworthy. This ambitious project will be evaluated on standard benchmarks for agents that are supporting smartphone users. The major aim of the project is to understand where and when current agents fail to reason consistently and augment them with a neuro-symbolic layer that can fix these reasoning shortcomings without compromising performance and scalability.
The PDRA will be part of the april Lab at the School of Informatics, University of Edinburgh which is ranked among the top schools in Europe for AI research according to CSRankings.
The PDRA will be supervised by Dr. Antonio Vergari, a leader in tractable probabilistic machine learning and neuro-symbolic AI, and will collaborate with researchers and engineers from the TTE-DE Lab.
PDRA Responsibilities
1. Conduct cutting‑edge research in LLM agents with neuro‑symbolic layers, building on our lab’s pioneering research on reliable and trustworthy ML.
2. Assist the TTE-DE team with benchmarking different failure models of foundation models and their safer neuro‑symbolic version.
3. Write scientific papers documenting the proposed methodology.
This position includes funding for international travel to attend conferences and offers access to our HPC infrastructure. The position is open to UK and international applicants, with visa sponsorship available. The role is advertised as full‑time (35 hours per week); however, we are open to considering part‑time or flexible working patterns, and to hybrid working (on a non‑contractual basis) that combines remote and on‑campus work.
Contact details for enquiries
Antonio Vergari, avergari@ed.ac.uk
Your skills and attributes for success
* A PhD or near completion in ML, MLSys, NLP or related areas of computer science / engineering / mathematics.
* Track record of research excellence, evidenced by e.g. publications in top‑tier venues.
* Experience in implementation of foundation models / LLMs, evidenced by e.g. published papers and projects on Github.
* Experience in implementation of neuro‑symbolic systems, evidenced by e.g. published papers and projects on Github.
#J-18808-Ljbffr