Saheed Faremi
PhD researcher, University College Cork · Data scientist
[email protected] · Available to work anywhere in Ireland
PhD researcher and data scientist with five years of experience building production software. I study what brief brain states represent and how they change over time. In industry, I apply machine learning to healthcare, finance and compliance.
Last updated November 2026
Research areas
- Brain and behaviour
- EEG microstates and brain-signal analysis; neuroscientific knowledge discovery; neuroimaging; nonlinear time-series analysis
- Explainable and reproducible AI
- Explainable Artificial Intelligence; mechanistic interpretability; reproducible machine learning
- Applications
- Deep learning for health and behaviour; production AI and data systems
Technical skills
- Brain-signal analysis:
- PyTorch; scikit-learn; MNE
- Applied AI and agents:
- Azure OpenAI; AI agents and tool use; prompt engineering; retrieval-augmented generation (RAG); document question answering; model fine-tuning
- Software & cloud engineering:
- Python; Go; TypeScript; SQL; FastAPI; Azure; CI/CD; SLURM; multi-GPU scheduling; memory-aware job allocation; automated testing
- Research evaluation:
- Testing across participants; statistical significance tests; correction for multiple comparisons; time-series and duration analysis
Education
PhD · University College Cork
In progress
Neural engineering and machine learning. Supervisor: Luca Longo.
MSc Computer Science · Technological University Dublin
Completed
Machine learning, deep learning, data mining, visualisation and statistics. 4.0/4.0 GPA (80/100).
BSc Information Technology · University of Eswatini
Completed
Machine learning, deep learning, data mining, visualisation and statistics. Second Class Honours, Upper Division (2.1).
Experience
PhD researcher · Artificial Intelligence and Cognitive Load Research Lab (AICL), University College Cork
In progress
- Compared image-based and electrode-based representations of brain activity on 203 recordings. The electrode-based approach explained 61.8% of the variation, versus 54.2% for the image-based approach, which grouped similar activity better.
- Analysed brain-activity recordings from 203 people to understand how activity changes from one state to another. Paired statistical tests showed that accounting for state duration represented these changes more accurately than the current state alone, improving the result from 55.7% to 63.7%.
- Showed that analysis settings can change average reported brain-state durations from 402 to 24 milliseconds. Using the same processing method for both approaches changed the image-based result from 143.2 to 71.0 milliseconds, close to the electrode result of 70.2 milliseconds.
- Evaluated 4,832 model configurations on SLURM-managed GPU and IBM Power9 systems, scoring 110 measures per model and testing consistency across participants.
Data scientist to Founding engineer · Etihuku (Curnance)
May 2021 to present
- Led a four-person team to develop a compliance dashboard for tracking legal obligations, document submissions, compliance scores and risk levels, reducing manual handling by 60%.
- Built a facial-recognition system for Know Your Customer (KYC) checks, using identity documents and liveness verification to flag potentially fraudulent user profiles for review. Developed automated checks to identify suspicious financial transactions, improving fraud detection by up to 35%.
- Built an LLM proposal generator from scratch for business bids, using RAG to turn past proposals, contracts and client requirements into seven-section drafts and cut manual preparation time by 80%.
Publications
Peer-reviewed
- AICS 2026, University College Dublin (accepted; proceedings to appear) · 2026 · Conference paper
- Brain Informatics · 2026 · Journal article
- IEEE ICTAS 2024 · 2024 · Conference paper
Preprints, registered protocols & doctoral work
- XAI 2026 (Late-breaking work + Doctoral Consortium track), Fortaleza, Brazil (arXiv preprint) · 2026 · Preprint
- OSF Registries (registered systematic-review protocol) · 2026 · Preprint
- XAI World Conference 2025, Doctoral Proposals track · 2025 · Workshop
Under review and manuscripts
- Cognitive Computation (manuscript in preparation) · 2026
- ICLR 2027 (under review; OpenReview #50003) · 2026
- Under review · 2026
Talks
- Temporal Dynamics and Latent-Space Interpretability of Generative EEG Microstate Segmentation.
34th Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2026), University College Dublin, Dublin, Ireland, 2026
- Interpretable EEG Microstate Discovery via Variational Deep Embedding.
XAI 2026 (Late-breaking work + Doctoral Consortium track), Fortaleza, Brazil, 2026
- Machine Learning Models for Predicting Malaria in Nigerian Children Under Five.
IEEE ICTAS 2024, 2024