This whole résumé also runs as a TUI over SSH — paste that into your terminal.
Ask my résumé
Backed by an agent grounded in the résumé below — it answers from the résumé and says so when something isn't there. It won't make things up.
Hiring? Paste a job description for an honest fit report
Think it could be a fit? Email me and let's talk it through — gaps included.
About
Senior software engineer and product owner with over a decade building web
applications end to end. I lead while staying hands-on — my goal is to guide a
team and still add value directly, whether that's writing code, shaping the
product, or working through a hard problem with the people building it.
Right now my focus is AI done well: agentic features grounded in real signals
that earn trust, not free-form output. I care about clear delivery, strong
teams, and software that solves the user's actual problem.
Build on an AI-first developer product as part of the engineering team — contributing to the agentic layer that grounds AI answers in real engineering signals (code, changes, deploys, runtime telemetry) instead of free-form output.
Act as customer zero — dogfood the product daily and feed findings back into delivery, and partner with principal engineers to tighten SLOs and alerting.
Led generative-AI delivery as Product Owner, including a natural-language assistant (Davis CoPilot) that turns plain English into complex DQL queries.
As Product Owner for the Strato Design System, prioritised the roadmap and aligned stakeholders for a charts and component library used by every app team across the company.
As Product Owner for Log Monitoring (powered by Grail), owned all UI delivery.
Delivered 85%+ of committed sprint work and cut incoming bugs from 4–6 per sprint to two or fewer per two-week sprint.
Build and optimise Angular / TypeScript front-ends and integrate closely with backend teams.
Delivered and maintained production web applications as a senior engineer.
Thomson Reuters
Frontend Developer · 2016 · Barcelona, Spain
GFT Group
Web Developer · 2015 — 2016 · Barcelona, Spain
Built and maintained features on an online platform within an agile/Scrum team, working directly with stakeholders.
SIGMA
Web Developer · 2012 — 2015 · Spain
Built and optimised software for universities in Java and JavaScript; supported and trained customers.
Leadership
I lead by staying close to the work. As a Product Owner I ran prioritisation,
research, and stakeholder alignment while still writing and reviewing code, so
direction and delivery never drifted apart.
I mentored three colleagues into Product Owner roles — walking them through
what the job really involves, having them shadow me through backlog refinement,
planning, and stakeholder conversations, then handing over real ownership while
I stayed on hand for support and gave regular, specific feedback as they grew
into it. Alongside that I moved the team off a single backlog-owning PO toward
distributed epic owners who run their own refinement and delivery, and built
onboarding tools to bring juniors and interns up to speed. Almost every epic
agreed with stakeholders shipped on time.
What I want next is to lead a team while still contributing to the work itself.
This résumé — a terminal UI you reach over SSH, a matching web page, and an agent you can talk to, all built in Go from one content source.
Go
SSH
AI agent
TUI
How this site works
The page you're reading is itself a work sample — here's what it demonstrates:
One Go binary, one content source — this résumé renders three ways (a terminal UI over SSH, this web page, and an AI agent you can talk to), all from a single YAML file.
The agent is grounded: it answers only from the résumé and says so when something isn't there, instead of inventing. Anything you paste is treated as untrusted data, never as instructions.
Guardrails: per-IP and global rate limits, a hard monthly/daily budget with a circuit breaker that survives restarts, and a response cache — so the agent can't be run up as a bill or a denial-of-service.
Resilience: it can fail over between two LLM providers, and degrades gracefully — if the agent is disabled or over budget, the rest of the résumé keeps working.
Locked down: a distroless, non-root, read-only container with all Linux capabilities dropped; a strict Content-Security-Policy (no inline scripts); and an SSH endpoint that can only ever drive the read-only TUI — no shell, exec, or filesystem.
It's tested: unit tests, a race-clean concurrency suite, and an optional live evaluation of the agent's grounding.