I study artificial intelligence and learn by building complete projects: from raw data to a model trained, evaluated without cheating and served behind an API. All of it with the code public.
Selected 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
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
AI Insight Assistant
An assistant that combines RAG and a SQL agent: it retrieves from a document corpus and queries a database, served with FastAPI and Streamlit and packaged in Docker. Code at github.com/delcenjo/ai-insight-assistant.
View project
RAG Document Assistant
A retrieval-augmented generation assistant over a document corpus: indexing, semantic retrieval and answers with source citations. Code at github.com/delcenjo/rag-document-assistant.
View project
LLM SQL Agent
An LLM agent that answers questions over a SQL database: it translates natural language into queries, runs them read-only and summarises the result. Code at github.com/delcenjo/llm-sql-agent.
View project
LLM Eval Harness
An evaluation harness that compares an LLM against baseline classifiers on a concrete task: reproducible metrics to tell when the LLM is worth it and when it is not. Code at github.com/delcenjo/llm-eval-harness.
View project
Text Summarizer
An abstractive text summariser with chunking for long documents: package, CLI and live demo. Code at github.com/delcenjo/text-summarizer.
View project
Customer Churn Prediction
End-to-end ML pipeline to predict telecom customer churn: data preparation, modelling and evaluation. Code at github.com/delcenjo/customer-churn-prediction.
View projectThere are more public projects on GitHub.
View all projectsCrafted with
Curious?
Creative technologist Building small universes with code *
From raw data to a deployed model
Machine Learning Pipelines
From raw data to a trained model: data preparation, leakage-free validation, model comparison and honest evaluation. Reproducible and tested, not a loose notebook.
See more
LLM Applications
RAG over documents, agents that query data and applications built on language models, with the evaluation needed to know whether they actually work.
See more
Deployment & MLOps
Getting the model out of the notebook: an inference API, containers, CI/CD, version registry and drift monitoring. So it does not stay a demo.
See more
Machine Learning
Deep Learning
MLOps
NLP & LLMs
RAG & embeddings
Model serving
Tabular data
Python
Every project starts from a simple idea: you do not understand a model until you train, evaluate and serve it yourself.
I am José, an artificial intelligence and machine learning student in Madrid. I learn by building projects end to end: data pipelines, ML models, LLM applications and the deployment so nothing stays in the notebook.
I try to make rigour weigh more than the demo: leakage-free validation, honest evaluation, calibrated probabilities and decisions tied to a real cost, not a pretty metric.
Right now: end-to-end projects across classic ML, RAG and agents, a suite of open-source tools published on PyPI, and contributions at Cylstat. Still learning every day.
RAG: verifiable answers over your documents
How retrieval-augmented generation works: indexing, semantic retrieval, chunking and evaluation. Why every answer should be able to cite where it comes from …
Shall we connect?
Let's talk: feedback, collaboration or an opportunity.
You can write to me about a project, a technical question, to give me feedback, or about an internship or a first junior role. I always reply.
Write to me