Shehab Mohamed

I am an Artificial Intelligence and Computer Vision Engineer with experience designing and deploying enterprise-grade Generative AI systems for clients across the United States and Singapore. I specialize in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), fine-tuning (QLoRA/PEFT), and production ML pipelines using Python, TensorFlow, PyTorch, and AWS.

I've led B2B adoption of ML recruitment tools, built end-to-end RAG pipelines for clinical summarization with HIPAA-compliant PHI anonymization, and orchestrated multi-agent LLM workflows that serve hundreds of daily queries. My projects include a financial-report analysis agent achieving high extraction accuracy and a real-time CV system for nystagmus detection validated in clinical pilots.

I focus on delivering scalable, compliant solutions that reduce manual work and inference latency while improving model fidelity and reducing hallucinations. I bring strong engineering discipline—DevOps, vector databases, and deployment experience—to translate research-grade models into reliable production systems.