Skip to content
Atmane Ayoub

Open to senior and staff AI/ML roles, and to select advisory engagements.

I build production AI systems that hold up outside the demo.

Atmane Ayoub, Senior AI/ML Engineer in Abu Dhabi. RAG, multi-agent workflows, document AI and computer vision — designed, shipped and measured in production for insurance and automotive businesses.

Latest release · Open source · my own project

Read the case study →

Jev-AR: Arabic intent routing in 10 ms

A 322M-parameter model that routes Gulf-Arabic messages to the right agent, tool or knowledge base — in one forward pass, locally, with routes supplied at request time.

60-route accuracy
83.4%
Latency (p50, GPU)
~10 ms
Unseen-domain RAG routing
38 / 40
Parameters
322M
“Atmane is a highly skilled AI and software engineer with a strong ability to turn technical concepts and specifications into robust, production-ready AI products. What particularly impressed me is his ability to cover the full development lifecycle, from understanding the requirements and designing the solution to implementation, integration, and deployment.”
Djamel MostefaVP Data & AI at JEMS · former Director of AI at First.tech · managed atmane directly
“I had the pleasure of working with Atmane and found him to be a highly professional, knowledgeable, and dependable colleague. He has a strong technical understanding, approaches challenges with a positive attitude, and consistently works toward finding practical solutions.”
Fawaad AhmedHead of Development, eData Information Management · managed atmane directly

More recommendations →

Case studies

Selected work

All work →

Courses, tutorials, studies and notes

Learning in public

Browse everything →

About

Eight years of shipping software, five in AI

Senior AI/ML engineer with 8+ years of software engineering experience, including 5+ years in AI and machine learning. I design and deploy enterprise AI across generative and agentic AI, RAG, document intelligence, computer vision and predictive modelling — including the evaluation, inference optimisation, backend APIs, MLOps and secure on-premises deployment that make those systems dependable.

Experience, skills and education →

  1. 2025 – now

    Senior AI/ML Engineer

    First.tech Group

  2. 2023 – 2025

    AI/ML Engineer

    eData Information

  3. 2021 – 2023

    AI/ML Engineer & Data Scientist

    Independent contractor

  4. 2018 – 2021

    Full-Stack & Mobile Developer

    Independent contractor

Work with me

Hiring, or need a senior hand on a hard ML problem?

  • RAG & agent architecture review

    A focused review of your RAG or agent system — retrieval quality, failure modes, latency and cost — with a prioritised fix list.

  • Evaluation & production-readiness audit

    Build the evaluation set and harness your LLM system is missing, so every change ships with evidence instead of guesswork.

  • Fractional AI lead

    Part-time senior AI leadership for teams shipping their first production LLM, agent or document-AI systems.