AI, Data & Automation Engineer
From ML pipelines and LLM evaluation to APIs, operational automation and internal tools, I focus on the engineering around the model: data, workflow state, validation, interfaces and the path to something people can actually use.
01 AI systems with deterministic controls
02 ML pipelines with defensible evaluation
03 Data + workflow automation for operations
04 Product interfaces around technical systems
Selected work
Projects are ordered by what they prove: systems ownership, research depth, evaluation discipline and the ability to move beyond a notebook.
AI systems · product engineering
A safety-gated AI application platform where model workers can propose, but deterministic software owns workflow state, authorization and auditability.
LLM research · reproduction · domain adaptation
A reproduction of ACL 2025 TISER on Qwen2.5-7B, extended with a context-memory conflict probe and a professional-tennis temporal reasoning adaptation study.
tabular ML · feature engineering · imbalanced classification
An end-to-end credit-risk classification workflow that turns repayment behaviour into robust features, tunes the operating threshold and finished first on the course leaderboard.
NLP · data quality · evaluation discipline
A leakage-aware multiclass news classifier built around schema validation, duplicate analysis, drift checks, sparse text features and stratified cross-validation.
For teams
If a process still depends on copying between tools, recurring spreadsheets, manual research or people assembling the same context every week, there is usually a concrete automation problem underneath the “AI” conversation.
I can help map that problem, prototype the useful part and build the integrations, data path or internal tool around it. If deterministic automation is enough, I will not sell an LLM.
Experience
A short professional path, but one that already crosses backend engineering, data delivery, consulting and RevOps automation.
Jul 2026 — Present
papernest · Barcelona, Spain
Work across RevOps, data, AI and automation, with an emphasis on operational systems rather than isolated analyses.
Sep 2025 — Jul 2026
T.I. Telematica Informatica — client work with Accenture / Intesa Sanpaolo · Remote / Italy
Designed Python/SQL pipelines for cleaning, reconciliation, KPI generation, forecasting and repeatable validation on structured datasets.
Mar 2025 — Sep 2025
T.I. Telematica Informatica — client: Gruppo Centro Paghe · Turin, Italy
Developed Node.js services, REST APIs and workflow automation, including an internal RAG assistant for document querying.
Two useful next steps