Ahmad Alshemerty

I am a Python engineer and AI content specialist with 4+ years building automation scripts, backend utilities, and evaluation pipelines. I combine hands-on engineering with applied LLM prompt design and agent evaluation to deliver reproducible, test-covered solutions.

My background in pharmaceutics adds rigor in research methods, documentation, and QA, informing my approach to evaluation frameworks and technical reporting. I have designed scoring functions, log-parsing tools, and sandbox tests to assess LLM outputs for clarity, accuracy, and coherence.

I deliver Dockerized, well-documented tooling and CI-friendly workflows that integrate REST APIs and local media toolchains (MoviePy, ffmpeg). I am available for freelance or contract remote work and prioritize reproducibility, clear SOPs, and measurable evaluation criteria.