Everything you need to ship AI products
From first idea to self-hosted production — one senior engineer, end to end.
AI Chatbots & Conversational AI
Multichannel assistants that answer, qualify, and convert — on your website, WhatsApp, Instagram, and Messenger.
- Knowledge-base (RAG) answers grounded in your content
- Button-based, lead-gen, AI, and live-chat flows
- Integrations with your CRM, catalog, and tools
- One assistant across web, WhatsApp, Instagram & Messenger
AI Infrastructure & Orchestration
Own your AI stack — route models by cost, run locally, and keep it observable.
- Model routing & cost optimization (LiteLLM-style gateway)
- Local and hybrid LLM inference
- Multi-agent & MCP pipelines, vector databases
- LLM observability, TTS/STT
RAG & AI Integration
Bring AI to your own data and embed it where the work actually happens.
- Retrieval-augmented generation over your knowledge base
- AI features inside your existing software & workflows
- Evaluation, guardrails, and sensible fallbacks
Web, Web App & Mobile Development
Fast, accessible products — from marketing sites to web and mobile apps.
- Marketing sites & landing pages
- Web applications
- Mobile apps
- Modern, performant, accessible builds
Cloud, DevOps & Self-Hosting
Ship and run it reliably — deploy, secure, back up, and scale.
- Docker deployments & cloud setup
- Object storage (MinIO / S3), backups, databases
- IAM & auth (Zitadel, OAuth, RBAC)
- Zero-trust networking (Cloudflare, Tailscale)
Automation & Digital Transformation
Audit first, then automate — boost productivity and customer-facing workflows.
- Digital transformation strategy & audit
- Customer-support & lead-generation automation
- Productivity & internal workflow automation
How I work
A simple, proven process
Discover
We dig into your goals, data and constraints to find the highest-leverage opportunities.
Prototype
A working proof of concept in days — so we validate value before scaling.
Build
I engineer the production system with quality, security and scale baked in.
Ship & run
Deploy, monitor and iterate — self-hosted and cost-optimized.
FAQ
Frequently asked questions
What can you build?
AI chatbots and conversational AI, RAG systems, AI infrastructure and orchestration, full-stack web and mobile apps, plus cloud, DevOps and automation — typically end to end as a single senior engineer.
Do you work with clients remotely and worldwide?
Yes. I'm based in Valencia, Spain and work remotely with companies and founders globally — 250+ client projects across 30+ countries to date.
Can you take a project from idea to production?
Yes. I run a simple, proven process — discover, prototype, build, then ship and run — delivering production systems that are self-hosted, monitored and cost-optimized.
How do you price projects?
Pricing is project-based and scoped after a short intro call, so you get a clear quote for the actual work. Book a free 30-minute call to talk through your goals, timeline and budget.
Do you self-host AI and handle the infrastructure?
Yes. I specialise in self-hosted AI and infrastructure — deploying and orchestrating LLMs and supporting services on your own VPS or cloud, with security, monitoring and cost control built in.
Not sure where to start?
Tell me about your project and I'll recommend the right first step.