mmegy
Remote: Yes
Willing to relocate: Yes
Technologies: LLMs & agents OpenAI, Azure OpenAI; agentic workflows, tool use / function calling, structured outputs; RAG over Azure AI Search + vector DBs; prompt engineering, evals, and tuning for latency/cost (token budgeting, caching, concurrency control). Software engineering — Python (primary), SQL, REST & gRPC APIs, Spring Boot, Docker, AWS, GCP, Azure, Firebase, Git, Linux.
Résumé/CV: https://drive.google.com/file/d/1dook4rhBnSXDEkSWQrNecSi3jhs... Email: [email protected]
AI engineer (4 yrs) who puts LLMs into the loop of real, production products not demos. I build and ship: LLM-driven pipelines that turn raw documents into structured outputs via function calling; RAG systems that ground answers in your own data and cut hallucinations; agentic workflows with tool use; and automated content/assessment generation. I focus on the parts that make LLM features actually hold up in production orchestration, evaluation, failure handling, and latency/cost tuning across many concurrent users. On top of solid backend engineering (Python, REST/gRPC APIs, cloud). Looking for Software engineer or AI/LLM engineering roles: agents, RAG, and LLM-backed product infrastructure.
LinkedIn: https://www.linkedin.com/in/MahmoudMohsenEg/ GitHub: https://github.com/MahmoudMohsenEgy