Available for projects and roles — Saudi Arabia · UAE · Europe

AI Engineer & AI Solutions Architect

I design and build production AI systems for organizations in Europe and the Gulf.

RAG pipelines, agentic workflows, and bilingual Arabic–English assistants — taken from requirements and architecture through deployment and evaluation.

0.93Hit@5 — legal RAG · 120-query eval
0.61 → 0.89Arabic Recall@10 · morphology + hybrid
~12Saudi enterprise accounts · agents
<950 msp95 TTFT · vLLM, concurrency 4–8
The system behind it

Engineering that survives production.

Not demos — deployed systems with evaluation gates, latency budgets, and data-residency constraints designed in from day one.

Bilingual retrieval, done properly

Clause-level chunking that preserves citation hierarchy, hybrid sparse + dense retrieval fused with RRF, then cross-encoder reranking — grounded generation that cites its sources and declines out-of-corpus questions.

QueryAR / EN
HybridBM25 + BGE-M3
RRFfusion
Rerankcross-enc
Answercited ✓
Hit@5 0.93MRR@10 0.81120-query eval · self-reported
BM25 baseline
0.61
+ morphology + hybrid + RRF
0.89
Arabic Recall@10 — client corpora · self-reported

Arabic morphology

CAMeL-based tokenization that understands roots, not just strings.

استحقاق → root حقق

Evaluation gates in CI

Releases blocked until golden-set thresholds pass.

RAGAS faithfulness0.87 ✓
Golden set · 180qpass ✓
QLoRA adapter gate2 rejected

Latency budgets

vLLM + AWQ 4-bit on g5.xlarge, measured under load.

TTFT median ~420 msp95 <950 ms

Model routing

Local open-weight models for routine calls, frontier APIs where they earn it.

Llama 3.1 / Mistral local−68% per-token vs API-only

Air-gapped & on-prem

Built for Gulf data-residency reality.

Oracle Cloud air-gapped deploy
active enterprise use in 30 days

How I work

The part most AI projects skip is the part between the demo and production. That’s the part I own.

  1. Discovery

    Understand the process today, the constraints, and what would actually be better.

  2. Requirements & architecture

    Scope it, then design an architecture that fits your systems and data.

  3. Engineering

    Build with boring, reliable tools — Python, FastAPI, PostgreSQL, containers.

  4. Evaluation

    Prove behavior with structured evaluation (RAGAS, LLM-as-judge, human review).

  5. Deployment

    Ship it into your cloud or on-prem, with the data-residency posture you need.

  6. Monitoring & support

    Observability, drift and cost monitoring, and human-in-the-loop controls.

At a glance

Regions

Saudi Arabia · UAE · Europe

Languages

Arabic · English · French

Core stack

Python · FastAPI · PostgreSQL · AWS · LangGraph · RAGAS

Education

MSc Applied AI · BSc AI & Business

Get in touch

For organizations

Tell me what the process looks like today, what you want to improve, and which systems or data are involved. I’ll reply with an honest read — including “you don’t need AI for this” when that’s the answer.

Discuss a project

For recruiters & hiring managers

Hiring for AI engineering, applied AI, forward-deployed, or AI architecture work? The case studies show how I approach systems; the CV has the full timeline.

Read About & CV
أهلاً وسهلاً — I work in Arabic, English, and French.