Download PDF
Back to home

Luis González Bernal

AI Engineer — Operations & Reliability

AI engineer with an SRE background. I build knowledge graphs, agents and evaluation pipelines that turn enterprise operational data (observability, ITSM, on-call and CMDB systems) into answers that can be audited. Strong foundation in Python, CI/CD and Kubernetes.

// Experience

AIOps Engineer

TCS (contractor at Roche) · Madrid, Spain

10/2025 — Current
  • Led the design and built the core of an operational knowledge graph and ontology over the company's observability, ITSM, CMDB and on-call systems. It stores no data: every query resolves live from the systems of record. Exposed to AI agents via an MCP server and a web UI, with per-user audit and role-based access. Served 5,000+ queries, 90% from AI agents; 88% answered with data at 0.6 s p50 latency.
  • Built an AI incident response agent (LangGraph, Claude, RAG + ChromaDB) that diagnoses incidents by correlating monitoring episodes, tickets and operational knowledge, and graduated it from L1 (suggest) to L2 (act under guardrails).
  • Built the evaluation layer for agents and skills: gold/silver/bronze datasets from human-verified incidents, weekly LLM-as-judge runs and usage telemetry. Defined autonomy levels that gate what every agent can do unsupervised.
  • Own a self-service recovery automation system: ~950 automated remediations/month across 4 orchestrators, used by 10+ teams to run their own recovery workflows.
  • Designed and built a PagerDuty Account Vending Machine: self-service platform (Terraform modules, Terraform Cloud, GitOps with Python + Jinja2 + GitLab CI/CD), adopted as the team's production onboarding system.
  • Built 15+ AI-powered skills automating sprint planning, incident management, documentation authoring and cross-system troubleshooting.
  • Run the central alert-correlation and incident-routing platform for 50+ application teams.

DevOps / SRE — Team Lead

Famytec (contractor at Roche) · Madrid, Spain

01/2022 — 09/2025
  • Ran the Rundeck automation platform at ~3,000 jobs/day and 99.97% SLI: built the CI/CD pipelines deploying it on Kubernetes (Ansible, Jenkins) and Python plugins for Splunk, ServiceNow and Vault.
  • Built Autodispatcher, a neural-network ticket classifier based on 18 months of assignment history, cutting mean assignment time from 45 min to under 5 min (90%).
  • Onboarded the operations center (GOC) and other teams onto Rundeck automation (e.g. bulk update of 600+ AWS accounts) through demo days and onboarding guides.
  • Led a group of SREs embedded across client projects, setting engineering standards and best practices.

Backend Developer / Data Analyst

Haciendas Bio · Badajoz, Spain (earlier: Agricultural Engineer, 2016–2017)

01/2018 — 12/2021
  • Shipped an ERP on AWS (Python, Django) for 40+ daily users, cutting data-recording time by 50%; built BI dashboards (R, SQL) that cut some activity costs by 20%.

Engineering case studies →

// Skills

AI & LLM: Claude, LangGraph, MCP (Model Context Protocol), RAG, ChromaDB, Knowledge Graphs & Ontologies (LinkML), LLM Evaluation (LLM-as-judge, golden datasets).

Observability & AIOps: Splunk ITSI, PagerDuty, ServiceNow, LogicMonitor, Alert Correlation.

DevOps & SRE: CI/CD, GitLab, Jenkins, Ansible, Docker, Kubernetes, Rundeck, Terraform, Git.

Backend & Data: Python, FastAPI, PostgreSQL, pytest, RBAC, JavaScript, Pandas, Django.

Cloud & Platform: AWS, GCP (Vertex AI), Linux, HashiCorp Vault.

Languages: English — Professional proficiency. Spanish — Native.

// Education

Master in Digital Transformation, University of Córdoba (2019) · Master & Degree in Agricultural Engineering, Universities of Córdoba and Extremadura (2011–2017)

// Teaching & Awards