Molecular biologist → Data Scientist. I build clean, reproducible analytics & ML pipelines that turn messy data into decisions.
PhD (Imperial College London) • Python/SQL • ML (sklearn) • upskilling in PyTorch/TensorFlow.

• 🧪 Background: 10+ years in genomics/CRISPR, now focused on ML & data products
• 🚀 I like shipping: tests, CI, simple deploys (Streamlit / FastAPI)
• 📍 Open to Data Scientist roles in London (primary); ready to relocate

Quantifies how “action-packed” each season was using Position Volatility Index & Lead-Change Rate.

• Streamlit app (interactive exploration) • Tested pipeline (pytest + CI)
• Coming next: bootstrap CIs, track/weather covariates
• 👉 Repo: https://github.com/GitDario79/F1_Golden_Era
• ▶️ Live demo: link coming soon

Product-style project: business framing → model → inference FastAPI.

• Random Forest baseline, explainability (SHAP), POST /predict endpoint
• Makefile + simple runbook; modular src/
• 👉 Repo: https://github.com/GitDario79/The-SpaceY-project
• ▶️ Live demo: link coming soon

Languages: Python, SQL, (R basics), Bash
ML: scikit-learn (classification, regression, clustering), feature engineering, model validation
Data: Pandas/NumPy, Plotly/Matplotlib, Scanpy (RNA-seq), UMAP/PCA
Product & Ops: Streamlit, FastAPI, GitHub Actions, pytest, Docker (basic)
Learning: PyTorch, TensorFlow, deployment patterns

• Reproducible structure (src/, notebooks/, tests/, app/)
• Short READMEs with “how to run” + screenshots
• Prefer small, shippable iterations over big rewrites

• LinkedIn: https://www.linkedin.com/in/dario-meacci-phd-a843a3a1/
• GitHub Projects: https://github.com/GitDario79
• Email: dario.mcc@gmail.com