Beyond Search
Agentic enterprise assistant for knowledge retrieval and validation workflows.
Machine Learning Engineer
Building practical AI systems people can trust and use.
I engineer production AI across LLMs, optimization, and forecasting. My focus is on measurable results combining LLM agents and classical ML to build systems that survive deployment and deliver value
Blend Optimizer SaaS
FastAPI-based no-code ML training, validation, and optimization service for clients.
Gate Vision Fraud Detection
Camera-only detection and tracking system deployed for airport and metro gates.
Jetson Edge Inference Stack
TensorRT/CUDA optimization for real-time multi-task inference on NVIDIA Jetson Orin.
Selected Systems
Applied AI and ML Engineering
ENTERPRISE KNOWLEDGE ASSISTANTS (RAG + AGENTS)
Built production assistants with retrieval and tool-use workflows for enterprise documentation, validation tasks, and writing support.
Related research artifacts
BLEND OPTIMIZER SAAS
Delivered a no-code ML service for training, validation, and optimization workflows using FastAPI, scikit-learn, and SQL for industrial clients.
GATE VISION FRAUD DETECTION
Built camera-based fraud detection with tracking and object detection, and improved edge deployment throughput on NVIDIA Jetson hardware.
Production Impact
From Prototype to Business Value
BeyondAI | Machine Learning Engineer
Jun 2021 - Present
- Built and deployed ML services for forecasting, optimization, and fraud detection with production monitoring.
- Co-developed Beyond Search for Aramco to turn static documents into an interactive assistant with agentic workflows.
- Built a no-code ML service (FastAPI + scikit-learn + SQL) for customer model training/validation/testing.
- Improved Jetson Orin inference throughput using TensorRT and CUDA for real-time CV workloads.
Ford | AI/ML Engineering Contractor
May 2025 - Sep 2025
- Implemented chat-history caching for internal LLM retrieval to reduce repeated calls and latency.
- Built Writing Coach Assistant with Gemini APIs, vector retrieval, and multi-step tool-use pipelines via LangChain.
- Launched Streamlit prototypes for employee feedback before internal deployment.
Core Capabilities
Engineering Stack
ML Engineering
Python, C++, SQL, PyTorch, TensorFlow, Scikit-learn
GenAI Stack
RAG pipelines, vector databases, LangChain, agentic orchestration, Vertex AI
MLOps & Delivery
Docker, Jenkins, MLflow, model versioning, CI/CD integration
Systems
FastAPI, Kafka, Spark, AWS EC2, GCP, edge optimization on NVIDIA Jetson
Research & Writing
Selected Publications
CREATING OPTIMIZED MACHINE LEARNING PIPELINES FOR PV POWER GENERATION FORECASTING USING THE GRID SEARCH AND TREE-BASED PIPELINE OPTIMIZATION TOOL
Cogent Engineering, 2024
Read paper
OPTIMIZING SOLAR ENERGY UTILIZATION IN FACILITIES USING MACHINE LEARNING-BASED SCHEDULING TECHNIQUES: A CASE STUDY
Renewable and Sustainable Energy Transition, 2025
Read paper
SYSTEMATIC EVALUATION OF INITIAL STATES AND EXPLORATION-EXPLOITATION STRATEGIES IN PID AUTO-TUNING: A FRAMEWORK-DRIVEN APPROACH APPLIED ON MOBILE ROBOTS
IEEE ARM, 2025
Read paper
FROM PLAYERS TO CHAMPIONS: A GENERALIZABLE MACHINE LEARNING APPROACH FOR MATCH OUTCOME PREDICTION WITH INSIGHTS FROM THE FIFA WORLD CUP
IEEE eIT, 2025
Read paperPatent: Localized Context-Based Screening of Language Model Inputs (Provisional Application)
Academic Background
Education
M.S. IN ARTIFICIAL INTELLIGENCE
University of Michigan-Dearborn, Dec 2025
View diplomaB.S. IN MECHATRONICS ENGINEERING
University of Jordan, Aug 2021