I build ML systems that ship to production — not just notebooks.
Built and shipped 3 ML systems while completing MSc at King's College London.
DistilBERT fine-tuned on 720,927 network flow records — a novel parser-free approach that treats tabular security data as natural language, with SHAP-based interpretability to explain every prediction.
Chose a weighted soft-vote ensemble (XGBoost, LightGBM, Logistic Regression) over a single model to improve signal stability across 34 technical and fundamental features. Added a Market Regime Classifier specifically to suppress signals during high-volatility periods — reducing false positives where a raw accuracy metric would miss the problem. SHAP explainability on every prediction means no black-box decisions. Real-time VADER NLP sentiment pipeline via n8n feeds into the main signal stack. Inference served through FastAPI; PostgreSQL stores backtests; Docker makes it portable.
Led a 4-member team to build a real-time gesture and voice recognition control system for accessibility applications. Combined computer vision (OpenCV) and NLP-based speech recognition to handle 50+ unique commands. Dataset augmentation, noise reduction, and hyperparameter tuning improved model responsiveness by 25%.
Built it for my own job search — then kept building. Runs at 9am daily via macOS launchd: Apify LinkedIn scraper + 50-employer career page scraper (Greenhouse, Lever, Ashby, Workday) → ATS keyword extraction → UK sponsor register check across 125,000 entries → recruiter enrichment → openpyxl workbook with conditional formatting. Zero cost, no LLM required for the daily run. A real tool with a real user.
ANN achieving 87% prediction accuracy on 10,000+ patient records. Feature selection and normalisation pipelines improved over baseline by 15%.
Stacking ensemble (GRNN, ENN, BPN) for solar power generation. 95% accuracy over 3 years of data; 18% improvement over single-model baselines.
Tamper-proof election prototype on Ethereum testnet. 20% transaction time reduction via smart contract optimisation. Presented at Tamil Nadu Government Academic Conference.
Advanced machine learning, big data analytics, statistical modelling. Dissertation: LLM fine-tuning for large-scale IoT intrusion detection. London, UK.
Automated 5+ reporting workflows in Power BI and Excel, cutting processing time by 30%. VBA and Python scripts reduced data entry by 40% across a 5-member analytics team.
CGPA: 8.35/10.0. Foundation in AI/ML, neural networks, data systems, and IoT. Best Presenter Award at NTU Singapore, 2023.
I'm looking for London-based AI/ML/Data roles starting mid-2026. If you have a role or just want to connect, reach out directly.