Work
I turn models into systems you can run.
I am building Illuma, legal AI for evidence and matter workflow, and I operate Luminous Giant, a Portugal consultancy that ships web applications, infrastructure, and AI your team can own.
- Current work
- Illuma + Luminous Giant
- Operating base
- Porto, Portugal
- Track record
- Payments, marketplaces, platforms
- Legal AIBuilding Illuma for evidence and matter workflow.
- Web, infra, and AILuminous Giant ships systems your team can own.
- Production pathsFrom prototype to a loop a team can run.
- Engineering depth
- 17+
years turning ambiguity into production systems
- International scale
- 6
markets across Asia and Europe with different operating constraints
- Team leverage
- 100+
engineers hired, coached, or mentored across distributed teams
- Automation proof
- 30s
AI-assisted audio mix workflow, down from a 15-minute manual pass
Thesis
Useful AI is not a feature. It is a production system with evidence, workflow, and accountability around it.
I built payment and marketplace infrastructure when uptime, fraud, compliance, and millions of daily transactions were the product. That operating muscle now shapes how I build AI systems.
The pattern is consistent: find the expert bottleneck, model the decision path, wire the data layer, then harden the workflow until a team can trust it in production.
Where I create leverage
Capabilities
Hire the work that turns a prototype into a system you can run.
Four kinds of work: production AI workflows, web applications you own, infrastructure under load, and engineering cadence.
Production AI workflows
Supervised agents, retrieval, and review gates that turn repetitive expert work into a loop a team can run.
Web applications you own
Sites, internal tools, and SaaS with repositories, pipelines, and credentials in the client's accounts.
Infrastructure under load
Cloud, edge, observability, and operations for systems that have to take traffic without heroics.
Engineering cadence
Hiring, delivery, incident habits, and the operating rhythm teams need to ship without chaos.
Method
From model possibility to operational habit.
I prefer short loops, visible risk, and working systems over long speculative roadmaps.
Map the bottleneck
Identify where expert judgment, latency, or repeated decisions constrain growth.
Prototype the loop
Build the smallest model + data + interface path that can prove useful work.
Harden the system
Add retrieval, evaluation, permissions, observability, and human review where risk demands it.
Ship the habit
Turn the workflow into team behavior with metrics, ownership, and iteration cadence.
Ventures
Three live products, not a portfolio wall.
Illuma is legal AI in production workflows. Luminous Giant ships web applications, infrastructure, and AI the client owns. PortoForYou is a founder-led Porto concierge.
Illuma
Legal AI · illuma.law
Legal AI for evidence and matter workflow — including multimodal evidence — with traceability instead of generic chatbot behavior.
Luminous Giant
Portugal consultancy · luminous-giant.com
A Portugal consultancy that ships web applications, infrastructure, and AI your team can own, with monitoring and a clean handoff.
PortoForYou
Porto concierge · portoforyou.com
A founder-led Porto concierge. We design private stays covering hotels, transfers, tables, and Douro days, then stay reachable while guests are here.
Stack
The useful work is where the layers meet.
Models, data, product logic, and operations are a map of how the work is built — not the offer itself.
- Model layer
LLMs, Gemini, prompt contracts, evaluation sets, fine-tuning, agent behavior, and task decomposition.
- LLMs
- Agent workflows
- Fine-tuning
- Prompt engineering
- Model evaluation
- Knowledge layer
The retrieval and memory plane that keeps work grounded in product, legal, media, or operational context.
- RAG pipelines
- Embeddings
- Vector search
- PostgreSQL
- Meilisearch
- Application layer
The product systems where users, permissions, payments, workflows, and business-critical state live.
- Laravel
- TypeScript
- Cloudflare Workers
- Microservices
- Payment systems
- Operations layer
The delivery environment: CI/CD, containers, observability, incident loops, and teams that own production.
- Docker
- Kubernetes
- AWS
- Linux
- GitHub Actions
Experience
Career proof across marketplaces, payments, ML platforms, and teams.
Expand each row for evidence, highlights, and technologies from the role.
Recommendations
People who have worked alongside me.
“Having worked 10 years ago and again hiring Miguel to work closely with me for the past 4 years tells a lot about how much trust and respect I have for him. Miguel Enes has a very entrepreneurial mindset that always sets him to find solutions and to move organisations forward. He does that relying on his profound and complete tech knowledge and on-hands experience, leading by example/execution and supporting his team along the way. I highly recommend him as an autonomous, energiser, tech-savvy and delivery oriented Engineering Manager.”
Writing
Recent writing.
What I'm Building in 2026
I am building Illuma, legal AI for evidence and matter workflow, and I operate Luminous Giant, a Portugal consultancy that ships web applications, infrastructure, and AI, from Porto. This note covers what I am shipping in 2026 and how both ventures share the same production-system thesis.
From Silence to Symphony: How We Built an AI-Powered Audio Mixing Engine with FFmpeg 8 and Intelligent Agents
We combine AI models, vector memory systems, and audio engineering rules to mix meditation mantras.
Orchestrating Multimedia Magic: How I Built Content Generation with Vizra ADK Workflows
I use Vizra ADK workflows to orchestrate multi-modal content generation across text, audio, and visual agents.
Contact
Bring a brief when the work needs to become a system.
Useful conversations: Luminous Giant builds — web applications, infrastructure, and AI — and Illuma for legal AI.