Multidisciplinary Data scientist with formal training in Biochemistry, Pharmacology, Neuroscience, **Applied Data Science & Machine learning ** and Computer Science with Software engineering.
| Domain | Stack & tooling (inline) |
|---|---|
| Backend / APIs | |
| Data engineering | |
| ML & MLOps | |
| DevOps & Cloud |  |
| Frontend |
- 🔍 Data visualisation – extending a real-time SQL + Python dashboard for GP data quality with automated split/merge detection.
- ⚙️ Data pipeline performance optimisation via Go micro-services – refactoring a high-throughput extract pipeline, meeting SLA targets and handing over to distributed teams.
- 🧪 Synthetic-data engineering – hardening a Kubernetes-hosted Django-Celery-Redis stack on Azure; CLI tooling and pen-test readiness.
- 🧠 NLP prototyping – re-training and productionising a dosage-instruction classifier, pushing precision/recall beyond 0.85.
- 🧬 Fault-injection with dummy test data – building controllable datasets to stress-test pipelines inside CI/CD.
- 🔗 QA automation – co-developing an automated QA library and CI hooks for linked datasets.
| Repo | Summary | Core tech |
|---|---|---|