About Me
I am an Artificial Intelligence researcher with expertise in emergent communication and machine learning applications for engineering problems. As a Research Fellow at the University of Southampton, I applied machine learning techniques to maritime engineering challenges, collaborating with industry partners to optimize car carrier designs through neural networks that estimate wave-induced resistance. My Ph.D. research investigated how autonomous agents develop languages from scratch, with a focus on temporal dynamics in those languages. I designed novel architectures enabling temporal referencing and understanding that improve strategy development and convergence in multi-agent systems. My work examining temporal relationships in interpretable emergent communication has been published in leading conferences including NeurIPS and ICLR. Since 2025, I am also a reviewer for NeurIPS.
- Artificial Intelligence
- Computational Linguistics
- Emergent Communication
- Reinforcement Learning
- Data-Centric Engineering
PhD in Artificial Intelligence, 2020–2025
University of Southampton
BSc in Computer Science, 2016–2020
University of Liverpool
Skills
PhD in Artificial Intelligence.
All publications and side projects coded in Python.
Worked with SLURM, Linux and HPC both during PhD and at Intel.
Automation pipeline, CI/CD testing.
Most of my work is in PyTorch (Lightning ⚡️).
Homelab cluster with Nextcloud, GitLab, IoT, email and others!
Made prototype-level PCBs.
Recently experimenting with sourdough bakes (focaccia 🍞!).
Experience
- Led AI implementation for a 2-month industry partnership optimising car carrier hull designs.
- Architected custom neural networks that accurately predict wave-induced resistance.
- Developed specialized loss functions tailored for maritime experimental data analysis.
- Delivered predictive models that accelerated added resistance calculations by 100x compared to traditional semi-empirical methods.
- Expertise: Scientific ML, PyTorch, MLOps (MLflow), Python
- Thesis: Temporal Dynamics in Emergent Communication
- Supervised by Prof. Timothy Norman, Prof. Adam Sobey, and Prof. Federico Cerutti.
- Supported by UKRI EPSRC funding through the MINDS CDT
- Investigated the effect of time on communication protocols, improving agents’ strategy development and convergence speed by up to 50%.
- Designed an architecture necessary for the emergence of temporal referencing in agent communication, enabling efficient communication.
- Developed human-interpretability measures for an emergent language containing local spatio-temporal relationships.
- Built end-to-end ML pipelines for agent training and evaluation.
- PhD defended with no corrections.
- Expertise: AI/ML, Python, PyTorch (Lightning), Ray (RLLib).
- Professional Skills: Research impact, research communication, academic collaboration.
- Managed client-facing HPC and Cloud facilities, ensuring optimal performance.
- Collaborated on pre-production hardware projects, developing technical solutions.
- Created deployment documentation and automation scripts to improve system efficiency.
- Expertise: HPC, Cloud, Bash, Linux, Server Hardware.
- Developed Bash and SQL scripts for customer data analysis using AWS services.
- Progressed from intern to part-time role across multiple projects.
- Expertise: Big Data, Amazon AWS (EC2, S3, Redshift), SQL, Bash.
Publications
Talks & Events
