I’m an AI Engineer building production-ready Retrieval-Augmented Generation (RAG), LLM agent workflows, and Document AI solutions for regulated and high-stakes domains like legal and tax. I’ve worked across the full lifecycle—from designing hybrid retrieval and reranking pipelines to shipping fine-tuned models and measurable automation that reduces manual review work significantly. In recent roles, I’ve led and delivered enterprise systems for clients, including locally deployed RAG services and agentic document-processing pipelines with robust orchestration and evaluation. I enjoy turning complex AI requirements into reliable software—using modern stacks like FastAPI, Docker/Kubernetes, and Qdrant, with strong observability and testing practices to ensure quality in production.

Eduardo García Tímermans

I’m an AI Engineer building production-ready Retrieval-Augmented Generation (RAG), LLM agent workflows, and Document AI solutions for regulated and high-stakes domains like legal and tax. I’ve worked across the full lifecycle—from designing hybrid retrieval and reranking pipelines to shipping fine-tuned models and measurable automation that reduces manual review work significantly. In recent roles, I’ve led and delivered enterprise systems for clients, including locally deployed RAG services and agentic document-processing pipelines with robust orchestration and evaluation. I enjoy turning complex AI requirements into reliable software—using modern stacks like FastAPI, Docker/Kubernetes, and Qdrant, with strong observability and testing practices to ensure quality in production.

Available to hire

I’m an AI Engineer building production-ready Retrieval-Augmented Generation (RAG), LLM agent workflows, and Document AI solutions for regulated and high-stakes domains like legal and tax. I’ve worked across the full lifecycle—from designing hybrid retrieval and reranking pipelines to shipping fine-tuned models and measurable automation that reduces manual review work significantly.

In recent roles, I’ve led and delivered enterprise systems for clients, including locally deployed RAG services and agentic document-processing pipelines with robust orchestration and evaluation. I enjoy turning complex AI requirements into reliable software—using modern stacks like FastAPI, Docker/Kubernetes, and Qdrant, with strong observability and testing practices to ensure quality in production.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Beginner
Beginner
See more

Language

Spanish; Castilian
Fluent
English
Advanced
Turkish
Beginner

Work Experience

AI Engineer at Securitas Direct (Verisure Group)
June 1, 2026 - Present
Designs and develops AI-driven solutions and internal tooling on enterprise-scale production data within an in-house multinational AI department.
AI Engineer, AI Department at Securitas Direct (Verisure Group)
June 1, 2026 - Present
Designs and develops AI-driven solutions and internal tooling for enterprise-scale production data within an in-house AI department at a global multinational.
AI Consultant (Freelance)
January 1, 2026 - June 30, 2026
Delivered a production RAG system over 50+ IRS tax-compliance documents for a US client using Ollama, Qdrant, FastAPI, and Open WebUI. The solution was deployed 100% locally in Docker with zero cloud dependencies, using parent-child chunking and a three-layer isolation architecture, cutting manual document review time by 70–85%. Also automated processing of Spanish regulatory form Modelo 790 (tasa 052) using n8n and LLM extraction pipelines, reducing manual completion time by 75–90% per request.
AI Tech Lead at Icod Systems
May 1, 2025 - May 31, 2026
Led an AI/ML engineering team owning architecture and delivery of production systems. Built a document classification pipeline with real-time verification checks to reduce manual review time by 70–85%. Implemented end-to-end LLM fine-tuning workflows (LoRA/QLoRA) on proprietary datasets, improving task accuracy by 25–40% and reducing inference cost by 50–70% versus general-purpose API alternatives. Shipped agentic AI workflows with autonomous tool selection and multi-step reasoning for document processing automation, plus high-throughput, low-latency data pipelines enabling real-time verification loops. Managed the full MLOps lifecycle (training, evaluation, model versioning, containerized deployment, and CI/CD) and built REST/streaming APIs integrating AI models with front-end products.
Full Stack Developer at Nartex Software, S.L.
March 1, 2023 - May 31, 2025
Built modern web applications with React/TypeScript and Node.js and implemented secure authentication and authorization (OAuth2, JWT, RBAC). Designed RESTful APIs and microservices across JavaScript, Java, Python, and Go within Scrum/Kanban teams.

Education

BSc in Computer Engineering at Universidad de La Laguna
January 1, 2023 - January 1, 2023
Computer Science (Erasmus) at University of Hradec Králové
January 11, 2030 - September 2, 2026
OpenAI with Azure at NALLAM
January 1, 2024 - January 1, 2024
Java Certification at Core Networks SL
January 1, 2024 - January 1, 2024
BSc in Computer Engineering at Universidad de La Laguna, Spain
January 1, 2023 - December 31, 2023
Computer Science (Erasmus) at University of Hradec Králové, Czechia
January 11, 2030 - September 2, 2026
OpenAI with Azure at NALLAM
January 1, 2024 - December 31, 2024
Java Certification at Core Networks SL
January 1, 2024 - December 31, 2024

Qualifications

OpenAI with Azure
January 1, 2024 - January 1, 2024
Java Certification
January 1, 2024 - January 1, 2024
OpenAI with Azure
January 1, 2024 - September 2, 2026
Java Certification
January 1, 2024 - September 2, 2026

Industry Experience

Financial Services, Professional Services, Software & Internet, Computers & Electronics, Government, Healthcare