Miguel Sánchez Duránsenior software engineer · AI systems · DubaiSoftware engineering and applied AI.

working onapplied ai, data analysis, machine learning, full-stack software, agent workflows

I combine full-stack engineering with applied AI, data analysis, and model evaluation.

Work and projects

Explore the work

Research

Finding information in documents, checking answers against sources, and evaluating model updates.

Products

Software for analysing data, managing workflows and working with AI.

Experiments

Small studies with recorded results, reproducible comparisons, and room for an idea to fail.

Experience

Fifteen years. Recent work first.

Weighted to current AI and full-stack work; earlier roles in brief.

  1. Senior Software Engineer, AI / full-stack

    Datafusion Systems·Since 2024 · Dubai, UAE

    • Working on retrieval, information extraction, and citation checks across multiple data sources.
    • LLM orchestration, LoRA/QLoRA fine-tuning, and evaluation on held-out datasets.

  2. Senior JavaScript Engineer

    Independent / consulting·2017–2024 · UK · USA · EMEA

    • Full-stack platforms for government, healthtech, and e-commerce in regulated, sensitive-data environments.
    • Early NLP, retrieval pipelines, and LLM-assisted features as the tooling matured.

  3. Earlier engineering roles

    Formedix · Ideagen · SlashMobility·2015–2017 · UK / Spain

Education

MIT

Applied AI and Data Science Program

2026–2027

Universidad de Sevilla

MSc, Web & Mobile Application Development

2011–2012

BSc, Computer Software Engineering

2007–2011

Writing

Notes from building careful AI.

October 20264 min read

Accuracy stayed the same. Confidence changed.

A worked example from Calibration Explorer: fit a temperature on separate data, measure what changes, and keep the evidence.

August 20268 min read

What 15 Years of Software Engineering Taught Me About AI Engineering

July 20269 min read

Building Reliable Agentic AI Systems

All writing

How I work

Full-stack development

Connecting interfaces, services, and data.

Evaluation

Testing models and checking answers against source records.

Sensitive data

Local models and access controls where the work calls for them.

Coding with agents

Using agents with tests and review around their changes.

Notes on my approach

Selected tools

AI & NLP
RAG · LangGraph · MCP · spaCy · Sentence Transformers
Model training
PyTorch · Hugging Face Transformers · PEFT · LoRA / QLoRA · bitsandbytes
Data & evaluation
Python · Pandas · NumPy · Time series · Cross-validation
Frontend
Angular · TypeScript · React · RxJS · NgRx
Backend & databases
FastAPI · Node.js · GraphQL · MongoDB · SQL
Delivery
AWS · Azure · Docker · CI/CD · TDD

Let's build something real.

An engineering problem, a role, or a question about one of the tools: any of those is a good reason to write.

contact@miguelsanchez.co.ukDownload CVLinkedInGitHubHugging Face