Visionary Quality Engineering Architect with a strong foundation in DevOps culture, TestOps, and Agile methodologies. I specialize in bridging the gap between highly reliable software architectures and modern, AI-driven testing paradigms. By leveraging Agentic AI frameworks (LangChain, LangGraph, CrewAI) and utilizing advanced LLM coding assistants like Claude Code at a professional level, I design autonomous, scalable validation pipelines. I am passionate about embracing new technologies, driving technical strategy, and reducing project uncertainty through smart, AI-augmented engineering solutions.

Innovations & Contributions

  • Agentic Test Explorer (LangGraph, LangChain, Playwright): Engineered a product-agnostic, AI-driven exploratory test framework utilizing a LangGraph Swarm architecture. Configured seamlessly via YAML, it dynamically routes tasks to specialized QA personas and stress agents that drive real browsers to uncover bugs and edge cases.
    • Autonomous Execution: Powered by Claude and Google Gemini. Self-heals from UI errors, consults user-provided MCP servers/Agent Skills, and generates reproducible Playwright scripts and Markdown reports.
    • Intelligent PR Analysis: Analyzes GitHub PRs by extracting code diffs, feeding them to an LLM, and auto-generating targeted test missions for likely impacted UI areas.
  • AI Test Reviewer (CrewAI): Developed an AI-powered PR analysis tool using CrewAI that automatically highlights code coverage gaps and generates actionable test suggestions.
  • AI-Assisted Development: Professionally utilize Claude Code to rapidly prototype test frameworks, generate robust automation scripts, and optimize infrastructure deployments.
  • TestOps & Observability: Integrated CI-integrated synthetic monitoring using Prometheus Push Gateway. Built Grafana and Prometheus dashboards to track flaky tests and analyze historical behavior.
  • Scale & Traceability: Built a maintenance validation pipeline running E2E tests across 70+ systems. Linked GitHub boards to HTML test reports (including public AWS reports) for issue traceability.

Mentorship & Open Source Leadership

Currently mentoring two high-impact Google Summer of Code projects:

AI-Based Test Selection

Guiding the development of ML models to intelligently select E2E tests based on code coverage analysis.

AI-Powered Intelligent Monitoring & Root Cause Analysis

Mentoring the creation of a standalone AI agent for the Uyuni ecosystem. Processes Prometheus metrics, leverages LangChain and local/cloud LLMs (Ollama/Qwen, Gemini API), and autonomously triggers SaltStack diagnostic commands to push enriched root-cause explanations to AlertManager.

Professional Experience

QE Architect

SUSE Remote

2018 – Current
  • Drive the technical vision for the Quality Engineering team, evolving sustainable testing processes into AI-augmented workflows and aligning toolchains with PO/PM quality standards.
  • Function as a core technical advisor, utilizing data and AI tools to reduce uncertainty, refine estimations, and facilitate sprint planning.
  • Make critical technical decisions regarding test frameworks, Infrastructure as Code (IaC), and CI/CD pipelines.
  • Actively foster a culture of learning by sharing insights on DevOps, Automation, and QA, and co-creating/facilitating the monthly SUSE DevOps Meetup.

Senior SDET / Backend Developer

King (Activision Blizzard) Barcelona & London

2014 – 2018
  • Designed and developed a highly reliable Java test framework from scratch, reducing execution time on recurrent test tasks by 90%.
  • Contributed heavily to DevOps processes by containerizing applications and streamlining CI/CD using Jenkins and Git Hooks.
  • Developed backend features for games and web services, focusing on reusability and maintainability to boost monetization.

QA Lead

Telefónica Digital Barcelona

2009 – 2014
  • Led a team of five SDETs to launch a robust CDN platform, which currently serves as the backbone for Movistar TV.
  • Designed a high-speed Python BDD test framework running on RedHat servers to ensure rapid regression testing.
  • Evaluated the performance of commercial CDNs applying advanced network diagnostics, and managed test automation for R&D spanning iOS/Android and OpenStack.

Previous Engineering Roles

INRIA Nancy, France (2007 – 2009) Contributed to an open-source SOA platform and integrated web services on the BonitaSoft BPM solution. Presented findings at JavaOne 2009.
BULL S.A.S Grenoble, France (2006 – 2007) Designed BPM processes using XPDL and conducted in-depth performance and cluster analyses of BonitaSoft.

Speaking Engagements & Talks

  • SeleniumConf 2026: Quality on Autopilot: Scaling Testing in Uyuni
  • openSUSECon 2025: Quality on Autopilot: Scaling Testing in Uyuni
  • SeleniumConf 2025: Smart Test Selection for PRs Using Coverage
  • SUSECon 2022: Automated QA for Maintenance Updates