Research Data Systems
Capture, validation, and reporting pipelines that keep research data trustworthy from the field to the final report.
I build the systems behind useful data.
I’m Oluwadamilare Oyediran — I design and build research data systems, LIMS workflows, dashboards, and ML/NLP pipelines, turning scattered records into reliable, AI-ready data.
LIMS Platforms
Laboratory information systems that trace every sample, experiment, and result back to the work that produced it.
ML & NLP Pipelines
Reproducible pipelines that turn raw data and messy text into models, predictions, and structured signals.
Dashboards & Operational Tools
Decision-ready interfaces and internal tools that put the right data in front of the right people.
Platforms built for real workflows
The platform-level work that anchors how I think about data — each framed by the problem it solves.
TraceLab
In ProgressTraceLab is a laboratory information management system designed to turn sample handling, lab workflows, approvals, and reporting into a traceable system of record.
Sample integrity is the backbone of trustworthy lab results — lose the chain and everything downstream is in doubt.
Shows I can model a regulated, audit-heavy domain and turn it into a dependable system of record.
- Python
- FastAPI
- PostgreSQL
- SQL
- Alembic
- Next.js
- TypeScript
- Tailwind CSS
- Supabase
- Docker
- Docker Compose
ImpactBoard
In ProgressImpactBoard is a project monitoring system designed to turn scattered progress updates, deliverables, and documents into clear dashboards and stakeholder-ready views.
Programs are judged on progress, and progress stays invisible until updates, deliverables, and decisions are pulled into one legible view.
Shows I can turn fragmented progress reporting into a clear decision surface for non-technical stakeholders.
- Streamlit
- SQLite
- Python
- Next.js
- Supabase
Research Data Systems at a Research Institution
Experience / InternalAn experience-backed case study on research data workflows — from field data capture and validation to metadata, repositories, PostgreSQL, CKAN, FAIR principles, and AI-ready data foundations.
Agricultural research decisions ripple outward, so the data behind them has to hold up to scrutiny.
Shows I can operate inside real research workflows where data quality is non-negotiable.
- KoboToolbox
- ODK
- PostgreSQL
- CKAN
- Python
- FAIR workflows
Builds across ML, NLP, and operations
A cross-section of what I ship — from predictive models to NLP pipelines and lightweight operational tools.
Crop Yield Prediction
Machine LearningA machine-learning pipeline that estimates crop yield from agronomic and environmental features, covering data preparation, model training, and evaluation in a reproducible workflow.
- Python
- pandas
- scikit-learn
- Jupyter
Cross-Platform Sentiment Intelligence Pipeline
NLP & AIAn NLP pipeline that ingests content across platforms and produces sentiment and topic intelligence — normalising messy text into structured signals teams can monitor over time.
- Python
- NLP
- Transformers
- ETL
RSVP60
Product SystemsA mobile-first tool for managing event invites with seat-based logic — seat allocation per inviter, optional plus-one rules, a waitlist, and admin visibility.
- Next.js
- TypeScript
- Tailwind CSS
Systems thinking, applied
A few principles that shape every system I build — from the first schema to the last screen.
Workflow-first design
I start from how people actually work, then shape the system around that workflow — not the other way around.
Data integrity and traceability
Records are validated at entry and traceable back to their source, so results stay trustworthy over time.
Maintainable architecture
Clear boundaries and readable code keep a system easy to extend long after its first release.
Secure access and role boundaries
Access is scoped to roles by design, so people can see and change only what they should.
AI-ready data foundations
Well-structured, well-described data today is what makes reliable analytics and AI possible tomorrow.
Tools across the data lifecycle
My core stack is built around Python, PostgreSQL, FastAPI, Next.js, TypeScript, Supabase, Docker, and cloud deployment workflows.
- Python
- TypeScript
- SQL
- PostgreSQL
- Supabase
- pandas
- NumPy
- FastAPI
- REST APIs
- Alembic
- Next.js
- React
- Tailwind CSS
- scikit-learn
- PyTorch
- XGBoost
- model evaluation
- Hugging Face
- sentiment analysis
- text classification
- chatbot workflows
- Vercel
- Render
- AWS basics
- Docker
- Docker Compose
- Git
- GitHub
- KoboToolbox
- ODK
- CKAN
- FAIR workflows
- metadata
- Streamlit
- Matplotlib
- Excel
- reporting dashboards
Interested in data systems, research software, or AI-ready workflows?
I’m always happy to talk through a problem, a dataset, or a system that needs building. Reach out and let’s figure out the right approach.