I build AI
that survives your audit

Javier Pontón González is a Forward Deployed Engineer and AI Engineer based in Asturias, Spain, working fully remotely for clients in the EU, UK and US. He embeds with the customer team, scopes the use case against their real data, builds on their infrastructure and stays through production and handover. The systems themselves are AI agents and multi-agent workflows with LangChain, LangGraph and MCP, Retrieval-Augmented Generation with embeddings and cross-encoder reranking, structured document extraction with vision-language models, and model serving on AWS Bedrock and Google Vertex AI or fully self-hosted and air-gapped. He has seven years of production backend engineering behind that, for Iberia, KPN, Mercadona, Inditex, Openbank and Idealista.

A Forward Deployed Engineer embeds with the customer team instead of delivering from the outside: scoping the use case against the customer real data, building on the customer infrastructure, and staying through production operation and handover. Javier has held the title on two engagements, which ran in parallel. At Iberia, S.A. he has been Forward Deployed Engineer since February 2026, technical owner of the fare pricing domain and of the MCP server and RAG service built on top of it. For a confidential IT systems integrator in Saudi Arabia, from July to August 2026, he was the sole engineer on an air-gapped multi-agent tender-response platform delivered inside the customer isolated on-premise network under Saudi PDPL and NCA requirements.

Yes, and the choice is made per use case. He deployed managed model serving on AWS Bedrock and Google Vertex AI to production at Iberia alongside self-hosted inference, deciding between them on latency, cost, data privacy, scalability and freedom of model choice, all of it integrated with the MCP server and the RAG service under OpenTelemetry and Dynatrace. At the other end of the range he delivered a fully air-gapped platform in Saudi Arabia with no external API call at all, benchmarking Qwen3, DeepSeek, Falcon-H1 Arabic and ALLaM under vLLM and Ollama.

Yes. He works as an Independent Consultant (Freelance / B2B Contractor) invoiced from Spain, is available immediately for up to 40 hours a week, and works fully remotely across EU, UK and US time zones. He takes both long-running forward-deployed engagements and shorter scoped work such as a two-week AI feasibility assessment. He can be reached at [email protected] or +34 623 920 307.

He built a production Model Context Protocol server and a RAG service over engineering documentation at Iberia, using embeddings, hybrid search and cross-encoder reranking, instrumented with OpenTelemetry and Dynatrace. As sole engineer for a Saudi systems integrator he architected a two-agent system for Arabic public-tender response, combining structured extraction from vendor quotations with RAG and Arabic OCR over RFPs of hundreds of pages, scoring 90%+ field-level precision and recall on the golden dataset before go-live. He also ships RAG in his own products: Facturias retrieves over Spanish tax regulation, and Grabia retrieves over a local meeting archive.

Yes, this is a core specialisation. He designed and delivered a fully air-gapped multi-agent platform for a Saudi systems integrator under PDPL and NCA requirements: model-agnostic architecture against OpenAI-compatible APIs, benchmarking of Qwen3, DeepSeek, Falcon-H1 Arabic and ALLaM, GPU and VRAM sizing for vLLM and Ollama serving, and no data leaving the client network. His own products run self-hosted vision-language models for the same reason, including GDPR special-category data in ZORRO.

Evaluation is defined before the build. A golden dataset representing real inputs, field-level precision and recall as the scoring rubric, regression runs on every prompt or model change, LLM-as-a-judge and human evaluation where the output is subjective, and hit rate and MRR for the retrieval layer. Everything is instrumented with OpenTelemetry so latency, token cost and failure modes are visible per agent step.

Four live products as founder and sole engineer. Facturias (facturias.es) is a multimodal invoice-processing SaaS with a self-hosted vision-language model and RAG over Spanish tax regulation. ZORRO (somoszorro.com) is a dating app for the gay and queer community on iOS and Android with semantic matchmaking and self-hosted photo moderation. Apunta (apuntapp.com) is a multi-tenant SaaS for shooting clubs owned end to end from custom NFC hardware to the mobile app. Grabia is a fully local meeting-intelligence pipeline running on a private inference node.

Python, Java, Kotlin and Elixir on the language side. FastAPI and Spring Boot for services. LangChain, LangGraph and MCP for agents. PostgreSQL with pgvector, Elasticsearch, Redis, DynamoDB and MongoDB for data. Kafka for events. vLLM, Ollama and mistral.rs for self-hosted inference. AWS, Azure and GCP with Docker and Kubernetes. Hexagonal architecture, DDD and TDD as the default way of building.

He is based in Asturias, Spain, in the Europe/Madrid time zone, and works fully remotely with clients across the EU, UK and US. He is a native Spanish speaker with professional working proficiency in English.