Hello 👋 | I’m Shanjidul Islam Sadhin, an AI Engineer who builds and deploys production-ready AI systems, with a focus on large-scale multimodal models. My work spans large language and vision models, retrieval-augmented generation (RAG), and the MLOps infrastructure required to serve them effectively.

I completed my B.Sc. in Computer Science & Engineering from American International University–Bangladesh, where I was a Dean’s Award recipient for academic excellence. My academic and professional journey has been driven by a strong interest in building intelligent systems that are both technically rigorous and practically impactful. My work spans vision-language models, retrieval-augmented generation (RAG), speech and emotion understanding, and full-stack AI system design. I have experience taking ideas from research and experimentation to production-ready deployments, with a strong focus on efficiency, scalability, and cost-aware model serving.

Professionally, I have worked across on-site, remote, and freelance roles, contributing to projects such as:

• Multimodal and computer vision systems deployed in real-world environments
• Speech and language pipelines optimized for cost and accuracy
• End-to-end AI applications combining LLMs, vector databases, and modern APIs

Alongside industry work, I have been actively involved in research, contributing to large-scale datasets and authoring work currently under review, with interests in image segmentation, action recognition, and applied deep learning.

I enjoy working at the boundary between research and engineering—where theory meets real users—and I’m particularly motivated by problems that require careful system design, thoughtful evaluation, and interdisciplinary thinking.