Our team has an immediate permanent opening for a Research Engineer
Responsibilities:
Research and apply state-of-the-art technologies to guide the synthesis process of neural symbolic architectures with the integration of LLMs/AI and Formal methods
Design and develop comprehensive testing strategies for LLMs-based AI systems, e.g., white box testing (examining internal components) and black box testing (evaluating system behaviour from an external perspective; assessing the coverage/activation patterns to understand the AI system, and improving performance
Design and develop formal modelling, analysis, and verification techniques to integrate symbolic information and reasoning within neural networks; ensure accurate interpretation and generation of LLMs-based AI system outputs
Work closely with researchers and engineers to apply advanced technologies into practical AI development lifecycle, and publish findings in relevant conferences and journals
#LI-TL1
Requirements
What you’ll bring to the team:
A Ph.D. degree in Formal Methods, Software Engineering, LLMs/AI, or a closely related field
Proven experience in research and development in related fields
Knowledge of formal reasoning and testing techniques
Understanding of LLMs/AI techniques and their limitations
Strong programming skills
Ability to collaborate effectively with interdisciplinary teams
Adept at identifying and solving complex technical challenges
