Madrid · Europe · RemoteAvailable now

Sami Halawa —Staff AI Engineer & Production AI Architect

Specializing in Multi-Agent Orchestration, High-Throughput RAG Systems, and Production FastAPI/TypeScript Backends.

Available for Direct B2B Contracting, Fractional AI Leadership & Advisory, and open to staff-level full-time roles (Madrid · Europe · Remote | ES / EN / 中文)

Four production system pillars

Every shipped system maps to one of four architectures.

Each one is demonstrated through client projects, collaborations and personal products. Every project is grouped by type on the projects page.

01

Multi-Agent Orchestration & Autonomous Tooling

Agent systems that research, decide and act across email, WhatsApp, voice and developer environments, with an explicit operator checkpoint before external action.

Stack

  • Python
  • FastAPI
  • LangGraph
  • Custom MCP tooling
  • Async execution
  • Human-in-the-loop
02

High-Throughput RAG & Search Platforms

Retrieval, ranking and assistant layers that serve real marketplace traffic in Mandarin, Spanish and English, evaluated against operator-defined quality checks.

Stack

  • Vector DBs
  • BM25 hybrid search
  • Query DSL
  • Reranking
  • LLM-as-judge evals
03

Cloud Architecture, Cost Optimization & MLOps

Control planes, model routing and observability that keep AI products cheap to run and easy to operate, from managed cloud to self-hosted inference.

Stack

  • AWS
  • GCP
  • Hetzner / Docker control planes
  • Redis / PostgreSQL
  • LangSmith / Langfuse observability

Proof highlights

04

Regulated-Domain & Medical AI Systems

Clinical, legal and compliance workflows where image interpretation, reasoning, reporting and professional review stay separate and auditable.

Stack

  • Document intelligence designed for GDPR constraints
  • EU AI Act Article 50 transparency
  • Fine-tuned VLMs (DeepSeek-VL2)
  • Human review by design
Featured case studies

A client project, a collaboration and a personal product, with the architecture left in.

Each case study covers the operating problem, the system architecture and the outcome behind it. More case studies, including AutoClient and a live WhatsApp preview fix, are on the full index.

All five case studies
APOLO & medical workflow systems product interface
CollaborationTechnical lead · research and prototyping

APOLO & medical workflow systems

A family of medical-image, structured-reporting and clinical-learning prototypes with explicit human review, anchored by APOLO, a DeepSeek-VL2-tiny multimodal model for radiology and ophthalmology imaging published on Hugging Face.

The problem
Explore useful multimodal support without collapsing image interpretation, reasoning and professional review into one opaque step.
What I built
APOLO architecture and model artifacts, ophthalmology and radiology workflow experiments, reports and Umbramed learning tools.
Role: Technical lead · research and prototypingAPOLO · AutoIOL · AutoRad · UmbramedRead the case study
OULANG (欧浪AI) product interface
Personal projectProduct, engineering and operations lead

OULANG (欧浪AI)

A Mandarin-first marketplace and local-life product built for the Chinese community in Spain, live on web, iOS and Android.

The problem
Bring housing, jobs, services and community discovery into one coherent experience across languages and devices.
What I built
Web, iOS and Android surfaces with shared marketplace infrastructure, publishing, subscriptions and product analytics.
Role: Product, engineering and operations leadMarketplace · Local life · Mobile appsRead the case study
AutoClient revenue operations product interface
Personal projectProduct and engineering lead

AutoClient revenue operations

An agentic operating system for account research, enrichment, CRM work and multi-channel follow-up. A public LinkedIn recommendation cites 200+ qualified contacts in two weeks and a 30% lift in sales conversion.

The problem
Keep research, qualification and follow-up connected while preserving a clear operator checkpoint before external action.
What I built
Research and scoring workers, CRM synchronization, reporting, and email, WhatsApp and voice integrations.
Role: Product and engineering leadResearch & enrichment · CRM · Email · WhatsApp · voiceRead the case study
How I work

Staff-level AI engineering with end-to-end production ownership.

I combine agentic AI, RAG and automation with the full-stack engineering needed to put them into real products. My background in web platforms, operations and technical education supports that delivery without competing with its focus.

Hands-on by default: I move from product framing through Python and TypeScript implementation, APIs, data, deployment, observability and iteration without splitting the system into disconnected handoffs.
1

Engineer the full AI workflow

Retrieval, tools, structured outputs, APIs, data, interfaces, deployment and observability belong to one system.

2

Build for operation

Reliable AI work includes monitoring, human review and the real workflow around the model—not only a successful response.

3

Bridge product and engineering

Spanish, English and Mandarin delivery helps connect technical decisions with users, teams and executives.

  1. 01

    Digital design instruction · Megacursos.com

    Digital-design education supported by practical web systems and learning materials.

  2. 02

    Web platform engineering · Megawebs

    Full-stack web platforms, technical SEO, Linux operations and delivery.

  3. 03

    ML / LLMOps engineering · Agents AI Ltd

    Production AI workflows across agents, RAG, automation, deployment and observability.

Client projects, collaborations, personal projects and tutoring listed on the projects page ran alongside these roles as contracted, joint or owned work, not as additional employment.

Across the public work

Follow the work where it lives.

Explore the code, technical writing, open-source tools and videos.

Engagement options

Three ways to engage.

Each engagement is scoped around a production outcome, not a headcount. Start with a consultation and I will recommend the format that fits.

A

Direct B2B Systems Engineering

Hands-on design and delivery of production agentic systems, RAG platforms and FastAPI / TypeScript infrastructure, from architecture through deployment and observability.

Format
Project or monthly contract · fixed scope or retained capacity
Best for
Teams that need a production AI system shipped and operated, not a prototype.
Scope a build
B

Fractional CTO & AI Architecture Governance

Ongoing technical leadership: architecture decisions, model and vendor strategy, cost control, hiring support and delivery governance across your AI roadmap.

Format
$15K–$25K / month retainers
Best for
Founders and executives who need senior AI architecture ownership without a full-time hire.
Discuss a retainer
C

Technical Due Diligence & AI Code Audits

Five-day pre-acquisition reviews of AI codebases, infrastructure and data practices, delivered as a written risk and remediation report.

Format
5-day engagement · written report and debrief
Best for
Investors, private-equity teams and acquirers evaluating an AI product or team.
Request an audit

Every option starts with one consultation. Engagements can run alongside an existing team, and staff-level permanent roles are considered on the same basis.

Book a consultation