Generative AI systems,
taken from prototype to production.
I'm a Machine Learning Engineer and AI Researcher with 6+ years building agentic AI, RAG, and LLM fine-tuning systems on end-to-end MLOps pipelines across AWS and GCP — on a strong classical-ML and time-series foundation. Published researcher with 7 peer-reviewed papers and 560+ citations.
Almosafer
Research discipline, engineering delivery.
The rarer combination: someone who can defend a result in a Q1 journal and keep the same idea running on production infrastructure.
Agentic AI in production
Multi-step LLM workflows built as state machines — structured output validation, self-correction loops, tool calling, and fallback handling that survives real traffic.
Applied research that ships
7 peer-reviewed papers and 560+ citations, including a top-0.1% cited Computer Science paper — plus controlled LLM adaptation studies run on multi-GPU clusters.
MLOps that runs unattended
End-to-end pipelines on AWS SageMaker and MLflow: automated training, versioning, deployment, monitoring, and the CI/CD around them.
Forecasting & classical ML
Time-series and gradient-boosted models where the business case is measured in revenue and error bars — not demos.
Things I built.
Podcast Summarizer Agent
Agentic AI application that discovers, transcribes, and summarizes podcast episodes on its own.
Learn PyTorch in 5 Projects
A full-length applied deep learning course published on the freeCodeCamp.org channel.
Text-to-SQL LLM (Qwen2 Fine-Tune)
Fine-tuned Qwen2-Instruct that turns plain-language questions into executable SQL.
Arabic Medical QA: LoRA vs. Full Fine-Tuning
The open-source research codebase behind a Cluster Computing (Springer) submission.
Published, cited, peer-reviewed.
Healthcare AI, Arabic NLP, and LLM adaptation — including the most-cited paper in its cohort.
Breast cancer detection using artificial intelligence techniques: A systematic literature review
Artificial Intelligence in Medicine
Arabic fake news detection based on deep contextualized embedding models
Neural Computing and Applications
Alzheimer Detection using Different Deep Learning Methods with MRI Images
IEEE ASET — Advances in Science and Engineering Technology International Conferences
Machine Learning Specialist at Almosafer.
Agentic AI and GenAI systems in production for the largest travel company in the Middle East, alongside revenue forecasting and MLOps platform work.
- Re-architected a single-call LLM extraction system for airline booking emails into a multi-step agentic workflow (LangGraph, LangChain) with structured output validation, self-correction loops, and fallback handling, significantly improving extraction accuracy and reliability.
- Built an agentic voice AI system (Retell AI) with LLM-driven dialogue management and tool calling to assist customer service, optimizing response quality and call-handling latency for real-time customer interactions.
- Designed a post-call GenAI pipeline using LLM-based summarization, classification, and entity extraction to convert raw call transcripts into structured records automatically.
- Deployed a time-series forecasting system for flight add-on revenue, enabling revenue optimization decisions that increased add-on revenue by 55%.
Want the detail behind any of this?
Every number on this site traces back to a shipped system or a published paper. Happy to walk through either.