MSc Data Science graduate focused on applied AI, machine learning, reproducible analytics, and product-minded ML systems.
I build applied AI and machine learning projects that connect modelling decisions with real-world use: retrieval design, validation strategy, calibration, threshold trade-offs, interpretability, safety constraints, and clear communication of results. I recently completed an MSc in Data Science with Distinction from the University of Aberdeen and am targeting Machine Learning Engineer, Data Scientist, Applied AI Engineer, and early-career ML/Data roles in the UK.
AI-first maternal support prototype combining retrieval-augmented generation, safety-aware routing, and appointment-preparation workflows.
What it demonstrates: Applied AI product design, healthcare-focused RAG, safety-aware response handling, source-grounded answers, symptom-intent classification, visit-prep generation, privacy-conscious persistence, structured answer design, and full-stack AI system thinking.
Technologies and skills: Python, FastAPI, React, TypeScript, RAG, NLP, safety routing, retrieval evaluation, healthcare AI, backend API design, product UX, privacy-aware system design.
Public case study for an Android + ML digital wellbeing product designed to help gamers protect focus without deleting their games.
What it demonstrates: Founder-built product thinking, privacy-conscious architecture, focus protection workflows, recovery-first UX, app boundary design, behaviour-aware recommendation logic, and Play Store readiness.
Technologies and skills: Kotlin, Jetpack Compose, Firebase, on-device ML recommendation design, privacy-first architecture, Android product development, product UX.
Retrospective sepsis early-warning ML analysis using patient-grouped validation and decision-aware evaluation.
What it demonstrates: Temporal feature engineering, patient-grouped model validation, probability calibration, threshold and policy sweeps, alarm-burden analysis, lead-time analysis, and careful communication of healthcare ML limitations.
Technologies and skills: Python, pandas, scikit-learn, temporal ML, calibration, healthcare ML evaluation, reproducible analytics.
End-to-end churn prediction project focused on practical business value and explainable model outputs.
What it demonstrates: EDA, feature engineering, classification modelling, model comparison, explainability, and translating predictive signals into retention-focused business recommendations.
Technologies and skills: Python, pandas, scikit-learn, classification, EDA, model evaluation, SHAP/model explainability, business interpretation.
Computational design of RNA thermoswitches for high-temperature genetic control in Bacillus subtilis.
What it demonstrates: Scientific ML depth, computational biology research, sequence design, thermodynamic modelling, feature engineering, model evaluation, and research communication.
Technologies and skills: Python, NUPACK, pandas, scikit-learn, sequence design, computational biology, feature engineering, reproducible research workflows.
- Applied AI and machine learning: classification, model comparison, feature engineering, calibration, threshold analysis, explainability, RAG, and NLP workflows.
- Reproducible analytics: clear project structure, documented workflows, validation-aware evaluation, and result interpretation.
- Product-minded ML: connecting model behaviour with user experience, operational constraints, privacy, safety, and decision-making.
- Healthcare and safety-aware AI: source-grounded responses, safety routing, careful limitation handling, and decision-support framing.
- Domain range: AI healthcare assistants, digital wellbeing, clinical early-warning ML, business retention analytics, and computational biology.
- Core tools: Python, FastAPI, React, TypeScript, pandas, NumPy, scikit-learn, RAG, NLP, SHAP, SQL, Git, GitHub, Jupyter, VS Code, Kotlin, Jetpack Compose, Firebase.
I am currently focused on building production-minded AI and machine learning projects that are:
- Validated with realistic data-splitting and evaluation choices.
- Clear about trade-offs, limitations, and deployment assumptions.
- Designed for reproducibility and readable technical communication.
- Connected to business, product, healthcare, or scientific decision-making.
- Built with safety, privacy, and real user value in mind.
- LinkedIn: Md Abir Hossain
- Portfolio: Coming soon