Gawad User

I’m a Junior AI Engineer focused on building production-ready, LLM-powered systems—especially RAG-based customer support with real-time summarization and contextual Q&A. I enjoy turning complex AI ideas into reliable backend pipelines that teams can ship and maintain.

At Acwad Technology (Sep 2025 – Feb 2026), I developed an LLM-powered customer support system using RAG over an internal knowledge base with Python. I built AI safety mechanisms including PII redaction, prompt validation, and prompt engineering workflows, and delivered real-time AI features using PyTorch and TensorFlow.

I also optimize how systems run end-to-end: improving backend reliability and tuning SQL performance, while collaborating with cross-functional partners using Git and Docker for containerization. My goal is simple—deliver measurable accuracy gains and dependable latency in the parts that matter.

My projects reflect the same mindset. I built a real-time intelligent surveillance pipeline with anomaly detection, MQTT alerts, backend APIs, a Streamlit dashboard, and Docker, and improved accuracy from 55% to 75%. I’ve also created a Medical Literature RAG Summarizer with LLaMA, FAISS, Transformers, and Gradio, and designed a multi-agent research co-pilot for literature review, gap detection, and hypothesis generation using LangChain, ChromaDB, and a full RAG workflow.