Paul Iusztin is a founder, author, and senior AI engineer with nine years of hands-on experience building production-grade AI systems and shipping 20+ apps. He wrote the bestseller LLM Engineer's Handbook and leads the Agentic AI Engineering course, teaching end-to-end AI engineering from data collection to deployment, monitoring, and evaluation. Paul has driven MLOps and infrastructure work across startups and scaleups—optimizing batch pipelines, cutting latency and costs by large margins, and scaling RAG ingestion pipelines from 1.5k to 36k+ documents per hour. His background spans computer vision, real-time recommender systems, and autonomous systems, and he routinely combines deep learning research with pragmatic software patterns like IaC, CI/CD, and modular Python packages. Based in Timișoara, Romania, he builds content and community through Decoding AI to help engineers escape PoC purgatory and 10x their AI engineering skills. An interesting detail: beyond teaching and writing, he consistently focuses on transportable engineering primitives—reusable frameworks and deployment patterns—that make research-ready models reliably work in production.
8 years of coding experience
6 years of employment as a software developer
Master's degree, Machine Learning, Master's degree, Machine Learning at Politehnica University of Timisoara
🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴
Contributions:12 reviews, 70 PRs, 186 pushes in 1 year 4 months
3-pipeline-designawsbeambytewaxcicd
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.