{ "profileVersion": "1.0", "lastUpdated": "2026-09-04", "canonicalUrl": "https://infraphysics.net/about/cv", "identity": { "name": "Yago Mendoza", "headline": "Industrial engineer and applied AI engineer", "image": "https://infraphysics.net/avatar.jpg", "email": "contact@infraphysics.net", "location": "Spain", "sameAs": [ "https://github.com/yago-mendoza", "https://www.linkedin.com/in/yago-mendoza", "https://x.com/ymdatweets" ] }, "positioning": { "headline": "AI that survives contact with the real world.", "summary": [ "I am an industrial engineer and systems-oriented generalist with particular depth in applied AI evaluation, deployment and end-to-end product engineering.", "I use that breadth to connect domain, software and infrastructure constraints, structure ambiguous problems and build systems that work in practice." ], "professionalFocus": [ "Applied AI engineering", "AI evaluation and reliability", "AI systems and infrastructure", "End-to-end product engineering" ] }, "proof": [ { "metric": "70 → 93%", "description": "DxGPT evaluated diagnostic accuracy, improved through model selection, inference optimization and safety guardrails." }, { "metric": "≈700K", "description": "Queries per year served by the clinical AI system supported by that evaluation capability." }, { "metric": "0 → shipped", "description": "TrialGPT built end to end: document parsing, clinical extraction, matching, evaluation, UX, backend and Azure deployment." } ], "capabilities": [ "AI evaluation & model selection", "Production deployment & reliability", "End-to-end product engineering", "Systems integration under operational constraints" ], "experience": [ { "name": "Fundación 29 de Febrero", "role": "Applied AI Engineer", "date": "2025 – Present", "href": "https://foundation29.org/es", "intro": "Building and operating clinical AI systems where model behavior requires measurable evidence, resilient infrastructure and human review.", "bullets": [ "Built the organization’s first GenAI evaluation capability for model-selection and ship/no-ship decisions.", "Helped improve DxGPT’s evaluated diagnostic accuracy from approximately 70% to 93%.", "Built and shipped TrialGPT end to end, from medical-document parsing to evaluation, UX, backend and Azure deployment." ], "tags": "Clinical AI · Evaluation · Azure · Reliability" }, { "name": "Leadrank", "role": "Product Engineer · Independent", "date": "2026 – Present", "intro": "Building an AI product that turns unstructured email history into structured commercial intelligence for real-estate workflows.", "bullets": [ "Designed ingestion and extraction for historical and real-time email processing.", "Built entity resolution and matching across contacts, deals, buyer intent and properties.", "Validating workflows and product demand with agents in Barcelona and Madrid." ], "tags": "Product engineering · Extraction · Entity resolution · Validation" }, { "name": "UNE", "role": "AI Standards Committee · Independent", "date": "2026", "href": "https://www.une.org/encuentra-tu-norma/comites-tecnicos-de-normalizacion/comite?c=CTN%2071&n=5", "intro": "Participated independently in Spain’s mirror committee for European and international AI standardization.", "bullets": [ "Contributed through UNE CTN 71/SC 42 committee meetings and standards review.", "Studied evaluation, bias management, dataset quality, risk and conformity-assessment workflows." ], "tags": "AI standards · Evaluation · Risk · Conformity" }, { "name": "Sony Europe", "role": "ML & Distributed Systems Engineer", "date": "2024", "href": "https://www.sony.eu/", "intro": "Worked inside Sony Europe’s Brussels ML R&D lab across blockchain optimization, program synthesis and agent evaluation.", "bullets": [ "Designed execution-based agent evaluation using compilation, automated tests and network deployment.", "Took the research system end to end, from DSPy and LangChain experiments to orchestration and infrastructure.", "Operated the Hyperledger Besu network, SDK and monitoring stack; selected optimizations entered Sony’s work." ], "tags": "DSPy · LangChain · TypeScript · Hyperledger Besu" }, { "name": "TE Connectivity", "role": "Supply Chain Data & Automation Intern", "date": "2023", "href": "https://www.te.com/en/home.html", "intro": "Applied software and data engineering to operational supply-chain processes.", "bullets": [ "Automated inventory, CRM and bill-of-materials reporting with Python and SQL.", "Built internal pipelines and reporting tools to improve data quality and planning visibility." ], "tags": "Python · SQL · Supply chain · Automation" }, { "name": "CIMNE", "role": "Safety Engineering · EU LASH FIRE", "date": "Earlier", "href": "https://www.cimne.com/vnews/2/10847/lash-fire-improving-ro-ro-ship-fire-safety", "intro": "Worked on safety-critical engineering within the EU-funded LASH FIRE research project.", "bullets": [ "Contributed industrial engineering analysis where technical decisions met physical safety constraints." ], "tags": "Safety engineering · Research · Physical systems" } ], "education": [ { "name": "IIA", "role": "Executive Master's · Business Intelligence & Management", "date": "2024 – 2025", "href": "https://iia.es/producto/master-ejecutivo/", "intro": "Applied AI across machine learning, deep learning, NLP and computer vision, with governance and real-world industry work.", "tags": "Applied AI · Governance · NLP · Computer vision" }, { "name": "Schneider Electric", "role": "Certificate · Agile Project Management", "date": "Dec 2024", "href": "https://www.se.com/es/es/" }, { "name": "UPC · ETSEIB", "role": "MUEI · Industrial Engineering · IT for Industry", "date": "2022 – 2024", "href": "https://etseib.upc.edu/es/futuros-estudiantes/que-estudios/master-universitario-en-ingenieria-industrial" }, { "name": "DeepLearning.AI", "role": "Specialization · Machine Learning", "date": "Oct 2023", "href": "https://www.deeplearning.ai/specializations/machine-learning" }, { "name": "UPC · ETSEIB", "role": "GETI · Industrial Technologies Engineering", "date": "2017 – 2022", "href": "https://etseib.upc.edu/es/futuros-estudiantes/que-estudios/grado-en-ingenieria-en-tecnologias-industriales" }, { "name": "CC Academy", "role": "Master's · Blockchain Engineering", "date": "2025", "intro": "Decentralized systems, smart contracts, cryptography and production infrastructure across EVM and Hyperledger ecosystems.", "tags": "Solidity · EVM · Hyperledger · Docker · Kubernetes" }, { "name": "Independent practice", "role": "AI, software & systems", "date": "2016 – Present", "intro": "A continuous self-directed curriculum built from lectures, papers, source code, technical writing and projects that had to work.", "tags": "AI · Computing · Infrastructure · Control · Distributed systems" } ], "contentSemantics": { "projects": "First-person engineering work and the strongest evidence of things built or operated.", "bits2bricks": "Technical explanations intended to make mechanisms traversable.", "essays": "Essays and arguments. They represent the author's analysis, not an employer or formal reference source.", "wiki": "Atomic learning notes and conceptual connections. Coverage indicates active study, not equal professional proficiency in every topic." }, "selectedWork": [ { "id": "2718281", "title": "TrialGPT: from a medical report to a shortlist of eligible trials", "category": "projects", "description": "A clinical-trial matching tool built at Foundation 29: describe your case or upload a report, and TrialGPT finds relevant trials near you in ClinicalTrials.gov and the European CTIS register, checks the inclusion and exclusion criteria against your situation clause by clause, and drafts a message to the trial coordinator. Covers the 2025 build, its eligibility reasoner and its failure modes, and how the live product works a year on.", "url": "https://infraphysics.net/lab/projects/trialgpt-clinical-trial-matching" }, { "id": "3142718", "title": "Model-based fault detection in a two-tank system", "category": "bits2bricks", "description": "Model-based fault detection and isolation on a two-tank hydraulic plant under closed-loop control. Thirteen component relations are reduced by structural analysis to four analytical redundancy relations, evaluated as residuals on Simulink runs, thresholded on healthy data and matched against a fault-signature matrix. Covers detectability and isolability, the noise cost of differentiating level measurements, the failure of exact signature matching, and the calibration a physical installation would require.", "url": "https://infraphysics.net/blog/bits2bricks/two-tank-fault-detection" }, { "id": "3141592", "title": "A CRM for a health-tech startup, built solo in 72 hours", "category": "projects", "description": "A bespoke CRM for a health-tech startup, designed and shipped solo in 72 hours. A real product built as an experiment in AI-assisted engineering: 23 tables, 8 state machines, automated enrichment and stale-relationship detection.", "url": "https://infraphysics.net/lab/projects/health-tech-crm" }, { "id": "6184744", "title": "Building this site: a markdown compiler, a theme system and a second brain", "category": "projects", "description": "How a systems engineer built a personal site with a custom markdown compiler, a second brain, and an AI development partner (and what went wrong along the way).", "url": "https://infraphysics.net/lab/projects/building-infraphysics" }, { "id": "5917362", "title": "Transformers from scratch", "category": "bits2bricks", "description": "A patient, ground-up explanation of transformer architecture: how tokens become predictions, what attention really computes, where facts live, and why it all scales.", "url": "https://infraphysics.net/blog/bits2bricks/transformers-from-scratch" } ] }