Awais User

I’m an AI/ML Engineer and Full-Stack Developer specializing in LLM engineering, multi-agent orchestration, and production AI systems. I build production-ready RAG pipelines, design function/tool-calling agent schemas, and ship software in Python and TypeScript.

Currently, I’m deploying LLM systems at Enliven AI, where I fine-tune LLMs using LoRA/QLoRA (PEFT) with Python, TensorFlow, and PyTorch. I also engineer multi-step RAG pipelines with LangChain, FAISS, and Chroma DB to power knowledge-grounded chatbots and enterprise search with better retrieval accuracy and fewer hallucinations.

Before that, I’ve worked as a Freelance Developer, building AI automation tools like voice agents and LLM-powered features with third-party API orchestration. In my projects, I delivered a FastAPI microservices platform achieving 89.5% delay-prediction accuracy and $105,300 in tracked cost savings, plus an event-driven RabbitMQ/MQTT/Redis architecture with an 85% cache hit rate; I also built an AR watch try-on experience using YOLOv8 + MediaPipe with Three.js overlays at 240 fps, and a production multi-branch Restaurant POS with real-time kitchen display, RBAC, and 70–85% smaller API payloads.