I’m a machine-learning–oriented engineer working across data workflows, reproducible experimentation pipelines, backend services, and cloud-aligned development. My background in biomedical science, neuroscience research, and computing gives me a strong foundation for building reliable, privacy-conscious systems in health and research contexts.

I’ve worked with EEG, behavioural, and psychophysics datasets, timing-sensitive acquisition workflows, and structured ML pipelines—while also building backend components, ingestion pipelines, containerised environments, and early applied-AI prototypes.

🏆 Winner – NextGenAI Hackathon (2025) Contributed backend logic, data handling, workflow reliability features, and early scheduling functionality for a voice-assistive healthcare prototype delivered in 7 days.

I enjoy the intersection where data → modelling → engineering → clinical context meet, creating systems that are robust, explainable, and useful to real users.

⸻

Machine Learning & Data

• ML-ready datasets for real-world data
• reproducible pipelines · cross-validation · model evaluation
• feature engineering on behavioural & biosignal datasets
• experiment tracking & structure

Cloud & Applied AI Engineering

• backend components supporting data preparation & inference
• containerised experimentation environments
• lightweight cloud workflows | reproducible development setups
• clean API surfaces for ML and analytics workflows

Healthcare & Scientific Context

• PHI/PII-aware design
• QMS-informed workflow design
• data-governance mindset
• experimental design & statistical reasoning

⸻

💻 Languages

• Advanced: Python, C
• Intermediate: Go, Java
• Proficient: JavaScript, HTML/CSS

📊 Machine Learning & Data

• scikit-learn · NumPy · Pandas
• supervised pipelines · feature engineering · leakage prevention
• data cleaning · cross-validation & evaluation patterns
• exploratory analysis · statistical reasoning
• Learning: TensorFlow, MLflow, streaming (Kafka/Spark)

🧪 Biomedical & Signal Data

• EEG · behavioural & psychophysics datasets
• sampling rate considerations · timing sensitivity
• artefact awareness · MATLAB data-acquisition workflows

🧩 Backend & Systems

• FastAPI · Flask · REST APIs
• containerised workflows (Docker) · Linux · GitHub Actions
• reproducible environments · modular service patterns
• Learning: Kubernetes, API gateways, edge-compute patterns

☁️ Cloud Foundations

• GCP · Azure · AWS (foundational)
• cloud IAM basics · secrets/config management
• deployment hygiene & environment setup

🔐 Compliance & Healthcare

• QMS-awareness: ISO 9001/45001
• PHI/PII handling · privacy-by-design principles
• Learning: ISO 13485, HIPAA, FHIR, ISO 27001

⸻

👉 Portfolio Organisation (WIP)

I set this up so I could integrate my GitHub repos with Linear. Aiming for this to be the home of more polished, documented projects.

👉 This GitHub Account

Explorations, prototypes, and learning repositories.

Some applied-AI and ML projects aren't in my GitHub yet - feel free to ask about in-progress work.

⸻

• Machine learning on behavioural, biosignal & health datasets
• Data engineering supporting ML & experimentation
• Digital health & MedTech innovation
• Applied AI patterns for real workflows
• Cloud-aligned ML environments
• Systems that balance performance, reliability, and compliance

⸻

• Biosignal/time-series modelling
• MLOps foundations for reproducible experiments
• Secure cloud/edge pipelines for healthcare data
• Advanced applied-AI evaluation & safety
• Scientific computing & efficient Python/Go modules