David Loor
AI, Cloud & Web Solutions Architect
Currently consulting on AI integration, cloud architecture, and web modernization for a small set of clients. Open to senior engineering and tech leadership roles.
$ open recent-work
- RFP SearchAI-assisted opportunity discovery
- AIdaemonSelf-hosted agent runtime
- BannermarchPersistent strategy game
- MCP serversAgent-ready tools and integrations
Expertise & Skills
A production-focused toolkit shaped by 17+ years of delivery.
Career & Education
Professional experience
Web Tech Lead
I lead a cross-functional team of 4+ on government-focused AI and web projects. Building security-focused government solutions that combine AI, databases, and web technologies with high availability during national traffic surges.
Director of Web Development
Led and mentored a global team of 10+ developers across three continents on large-scale enterprise platforms. Managed Drupal and WordPress implementations with robust security, performance, and WCAG 2.1 accessibility standards.
Education
Computer Systems Engineering
DegreeEarned my degree in Computer and Information Sciences from Ecuador's top technical university, building a strong foundation in software engineering, algorithms, and computer science principles.
From the Blog
My agent kept losing facts it had already saved
AIdaemon could save a fact and then fail to find it when I asked for it. Semantic search ranks by what's on the same topic, so the short fact holding the real answer gets buried under wordier ones nearby. A reranker reads each candidate against the question and puts the right one back on top.
Jun 18, 2026aiLocal Gemma was too slow with AIdaemon until I fixed llama.cpp and the prompt size
I wanted AIdaemon on local Gemma 4 26B through llama.cpp, not Ollama. Generation ran at ~45 tok/s on an M4 Pro. Agent turns still felt stuck because prefill on 14k-token prompts took 8 to 9 seconds before the model wrote a single word.
Jun 8, 2026AIHow production-grade AI agents actually work
A plain-English walkthrough of the control plane, tool plane, memory, guardrails, sub-agents, and observability behind production-grade AI agents.
May 20, 2026Get in Touch
Have a system to modernize, an AI idea to validate, or a senior role to discuss?
Let's talk
Choose a quick call or send the context by email.
- AI integration
- Cloud architecture
- Web modernization
Query this site from your AI agent
This portfolio is exposed as a Model Context Protocol (MCP) server. Agents can search blog posts, read the profile, and request consultations directly. Works with Claude Desktop, Claude Code, Cursor, or any MCP client.
Available for select consulting engagements and senior roles