moajez lalani

I’m a results-driven LLM and Generative AI Engineer with a Computer Science Engineering background. I build and deploy intelligent applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and full-stack web development.

I’ve architected real-time LLM systems like an AI Interview System using FastAPI and LangChain—generating questions, evaluating answers, and providing performance feedback with async patterns for low latency. I also build autonomous agent workflows with LangGraph, integrating retrieval via Qdrant to improve context-aware accuracy.

Beyond engineering, I’ve contributed product-side impact through Product Requirement Documents (PRDs), technical specifications, and Agile/Scrum execution. At Expertrons, I translated requirements into Jira tickets and used RICE prioritization to align delivery with quarterly OKRs and North Star metrics.

I’m especially motivated by AI Engineering, LLM Product Development, and Full-Stack AI SaaS roles where I can combine model workflows, evaluation/observability (LangSmith), and practical product thinking to ship dependable, user-focused AI features.