Amando Martínez
Backend · Data & AI Engineer
Spain · open to remote roles across Europe hola@amandomv.dev linkedin.com/in/amandomv github.com/amandomv amandomv.dev
Profile
I'm a backend engineer who drifted into data and AI because that is where the interesting failure modes are. Most of my work is the part users never see: pipelines that ingest messy external sources, APIs that stay boring under load, and LLM stages that are measured rather than guessed at.
I build and automate systems with AI in the loop — not as a demo, but as the way the work gets done. That means LLM agents wired into real engineering workflows, custom tooling and MCP integrations around them, and evaluation harnesses so a model or prompt change is an experiment with a number attached instead of an argument.
Experience
Senior Software Engineer — Backend, Data & AI · Datamaran
Aug 2022 — Present
- Designed and shipped LLM-backed classification stages for the regulatory pipeline, replacing hand-maintained rules and holding quality while cutting per-document cost.
- Moved a batch report-processing workload onto Airflow, turning an opaque long-running job into observable, retryable tasks.
- Built FastAPI services over PostgreSQL and MongoDB following a strict repository → application → endpoint contract, so business rules live in one testable layer.
- Automated recurring engineering and delivery workflows with LLM agents and custom tooling, and build most of my systems with AI in the loop — design, implementation and iteration.
- Contributed to the Vue 3 front end (PrimeVue, Pinia) for the features I own end to end.
Software Engineer · Previous company
Jan 2019 — Jul 2022
- Outcome one.
- Outcome two.
Selected projects
Turnos Parcelas · 2025 — present
Monthly invoicing went from a full afternoon of manual work to a few clicks. The system has been running unattended in production since 2026, including a multi-email client notification flow and a PDF invoice layout that survives the printer.
Python · PostgreSQL · Neon · Railway · Vue
Fantasy Voley · 2024 — present
A working league with real players in it, refreshed automatically through the season, and a data model that survived a federation site redesign without a rewrite.
Python · PostgreSQL · Neon · Railway · Vue
Regulatory intelligence pipeline · 2023 — present
Classification stages that used to take weeks of rule-writing now take a prompt change and an evaluation run. Batch report processing moved onto Airflow in the same period, turning an opaque multi-hour job into observable, individually retryable tasks.
Python · FastAPI · Airflow · PostgreSQL · MongoDB · LLMs · AWS
Skills
- Languages:
- Python · TypeScript · JavaScript · SQL
- Backend:
- FastAPI · asyncio · SQLAlchemy · Pydantic · REST API design
- Building & automating with AI:
- AI-assisted development (Claude Code, agentic workflows) · Automating engineering workflows with LLM agents · Systems designed, built and iterated with AI in the loop · Custom tooling & MCP integrations · Evaluation harnesses for LLM features
- Data & AI:
- Airflow · LLM pipelines · Prompt & eval design · Elasticsearch · ETL
- Storage:
- PostgreSQL · MongoDB · Redis
- Platform:
- AWS · Docker · Kubernetes · GitHub Actions · Grafana · Sentry
- Front end:
- Vue 3 · Astro · Tailwind CSS
Education
Degree in Computer Engineering
University · 2015–2019
Languages
- Spanish:
- Native
- English:
- Professional working proficiency
Last updated: 2026-09