Data Scientist InternNaudit HPCN2026Journey
Here I bring together my professional experience, my education and the recognitions that have accompanied my journey.
Data Scientist InternNaudit HPCN2026
President & FounderGoogle Developer Group on Campus UAM2025 - present
WebmasterAUTOCENTER - VULCASAN SL2024 - 2025
Board MemberComputer Security Club (SEIF UAM)2023 - 2024
Independent EntrepreneurDripInLocker2021 - 2024
WaiterSaona2022
Bachelor's Degree in Data Science and EngineeringAutonomous University of Madrid2022 - 2026
Cloud Engineering TrainingGoogle Cloud2025 - present
Data EngineeringGoogle2025
Investors League: Challenge Your Portfolio Strategy LiveUAM + IronIA Fintech2025Data AnalyticsGoogle2024
Data EngineeringNanjing University2024
UAM Emprende ProgramAutonomous University of Madrid2023
Personal Training EducationTrainologym2021 - 2023Fundamentals of Digital MarketingGoogle Digital Garage2021
Academic Excellence ScholarshipCommunity of Madrid2024 and 20251st Place - UAM Investors LeagueAutonomous University of Madrid + IronIA Fintech20252nd Place - Cloud Agent Systems HackathonGoogle Cloud + Diverger2025
Academic Recognition for High AchievementColegio San José de Begoña2020 and 2021Projects
Surrogate models for finding optimal inputs
Gaussian processes, Bayesian optimization and Expected Improvement for finding strong configurations under a limited evaluation budget.
RoadGuard
Reliable road damage detection: cross-country transfer, confidence calibration, abstention policy and explainable maintenance prioritization.
BGG Review Intelligence
From BoardGameGeek reviews to structured opinion knowledge: linguistic preprocessing, sentiment classification and aspect-based analysis.
Image generation with diffusion models
Implementation of the SDE framework by Song et al.: denoising score matching training, samplers, conditional generation and imputation on CIFAR-10.
github.com/trentisiete
More projects on GitHub
Smaller experiments, works in progress and technical deep dives.
Visit GitHub ↗-
Preference optimization & RLHF benchmarking
DPO, PPO and related alignment methods.
-
Model-agnostic agentic systems
Traceable dynamic LangChain workflows, multi-agent coordination, dynamic tool and agent creation, A2A and Redis.
-
Clustering methods exploration
A practical comparison of strategies, assumptions and behaviour.
-
How I finished first among 240 participants
Five months of data science and real-time analytics on a large fund data lake to select the strongest portfolio.
— total views — online