Tools & technologies
Deployment and MLOps
Getting the model out of the notebook and keeping it alive: an inference API, containers, CI/CD, a version registry and drift monitoring.
Getting the model out of the notebook and keeping it alive: an inference API, containers, CI/CD, a version registry and drift monitoring.
Serving with guarantees
The same pipeline that trains is the one that serves, so preprocessing is identical. Schema-based input validation, decisions tied to a cost-based threshold and the model version recorded in every response.
Watching for drift
A reference profile of the training data and drift metrics (PSI) over live traffic, exposed to Prometheus and Grafana. The point is to learn the model is degrading without waiting for someone else to notice.
Operating locations
Studying in Madrid
Based in Madrid, learning in public: projects, open-source tools and collaborations, inside and outside Spain.
Info graphic
Decision flow
Train and serve, the same pipeline.
Info graphic
Friction map
Cost-based decisions.
Info graphic
Journey shape
Drift monitored.
Next projects:

Credit Risk Platform
End-to-end MLOps platform for credit-default scoring: reproducible training with a versioned model registry, a FastAPI inference API with input validation, PSI drift monitoring and a Prometheus and Grafana observability stack, all containerised with CI. Code at github.com/delcenjo/credit-risk-platform.
View project
Transformer from scratch
A GPT-style language model implemented from scratch in PyTorch: multi-head attention, causal masking and residual blocks written by hand, plus a byte-pair tokenizer and an ablation study. Code at github.com/delcenjo/transformer-from-scratch.
View project
This very site
This portfolio is hand-built with Next.js and deployed on Cloudflare Workers, with a model lab that runs entirely in the browser and continuous deployment on every commit. Code at github.com/jmweb-org/jmweb-pag-web.
View project
Credit Risk Model
Credit-default risk model with rigorous evaluation: a leakage-free pipeline, cross-validated model comparison, calibrated probabilities, a cost-based decision threshold and per-segment error analysis. Code at github.com/delcenjo/credit-risk.
View project