Skip to content

Amando Martínez Vivancos

Backend · Data & AI Engineer

Spain · open to remote roles across Europe [email protected] linkedin.com/in/amando-martínez-vivancos amandomv.dev

Profile

I'm a backend engineer who ended up in data and AI because that is where the interesting failure modes are. I joined Datamaran as a junior in 2022 and grew into the senior role there, which in practice meant owning systems end to end: the pipelines that read 20,000 news items and 200 legal sources a day — one of them 85% cheaper to run than when I inherited it, the other saving the legal team 70% of its report-processing time — plus the auth and sharing layers underneath the product and the observability that tells us when any of it breaks.

I build and automate with AI in the loop — not as a demo, but as the way the work gets done. That means LLM agents wired into real pipelines (a scraper that repairs itself instead of paging someone), evaluation harnesses so a model or prompt change is an experiment with a number attached, and AI-assisted development spread across repositories and delivery processes.

Experience

Senior Software Engineer — Backend, Data & AI · Datamaran

Oct 2022 — Present

Joined as Software Engineer (Oct 2022) · promoted to Senior in January 2026

  • Built the news intelligence pipeline that ingests, deduplicates, clusters and classifies 20,000+ news items a day with LLMs on Airflow 3 over Kubernetes — and cut its annual LLM bill by 85% — a six-figure sum down to a five-figure one — by ordering stages by cost and moving them to smaller models once evaluation showed no quality loss.
  • Built the regulatory pipeline over 200 legal and official sources — the entire scraping layer plus its AI self-healing loop, delivered in about a week with AI assistance — which cut the legal team’s report-processing time by 70%.
  • Shipped the application’s user management and authentication system, and the resource-sharing layer that makes live collaborative work possible across accounts.
  • Introduced and spread the engineering practices the team now works by: DDD, hexagonal architecture, TDD, shared linting and formatting standards, and proper database connection-pool management.
  • Led the adoption of AI-assisted development — agents and evaluation harnesses wired into pipelines, repositories and delivery processes, not just editor autocomplete.
  • Owns observability for the systems I build: Grafana dashboards and Sentry alerting, so failures surface as signal rather than as a customer email.
  • Works directly with stakeholders to turn customer needs into features, from scoping through to production.

Selected projects

News intelligence pipeline

Twenty thousand items a day flow through unattended, and the pipeline's annual LLM bill came down by 85% — from a six-figure sum to a five-figure one. Clustering cuts the volume reaching the expensive stages by a large factor, and more than one stage ended up on a smaller, cheaper model once the evaluation showed it matched the larger one on the task that mattered.

Python · Airflow 3 · Kubernetes · LLMs · PostgreSQL · MongoDB · Elasticsearch · AWS

Self-healing regulatory pipeline

Report processing now takes the legal team 70% less time than before. The whole scraping layer covering all 200 sources, self-healing loop included, was built in about a week with AI assistance — work that would previously have been months of hand-written parsers. Sources that break heal themselves instead of paging someone, and a classification change is a prompt edit plus an evaluation run rather than weeks of rule-writing.

Python · Airflow · LLM agents · PostgreSQL · MongoDB · Elasticsearch · AWS

Gestión Guarda Rural

Monthly invoicing went from an afternoon of manual work to a few clicks. Built and shipped in weeks rather than months, including multi-recipient client notifications and a PDF invoice layout that survives contact with a real printer — the whole thing sitting on a deploy pipeline that only promotes what passed against a production-shaped database branch.

Python · PostgreSQL · Neon · Railway · Vue

Fantasy Voley

A working league built end to end — ingestion, scoring engine and front end — kept in sync automatically through the season, on a data model that survived a federation site redesign without a rewrite. Public launch is next.

Python · PostgreSQL · Neon · Railway · Vue

Skills

Languages:
Python · TypeScript · JavaScript · SQL
Backend:
FastAPI · asyncio · SQLAlchemy · Pydantic · REST API design · Connection pooling
Building & automating with AI:
AI-assisted development (agentic workflows, Claude Code) · Self-healing pipelines driven by LLM agents · Evaluation harnesses for LLM stages · Prompt and model cost/accuracy tuning · Custom tooling & MCP integrations
Data platform:
Airflow 3 · Kubernetes · Large-scale scraping · Clustering & deduplication · ETL
Architecture:
Domain-Driven Design · Hexagonal architecture · TDD · SOLID
Storage:
PostgreSQL · MongoDB · Elasticsearch · Redis
Platform & observability:
AWS · Docker · GitHub Actions · Grafana · Sentry
Front end:
Vue 3 · Astro · Tailwind CSS

Education

BSc in Computer Engineering — Computation specialisation

Universitat Politècnica de València · 2018–2022

Languages

Spanish:
Native
English:
Professional working proficiency

Last updated: 2026-09