I’m Sai — an Applied AI and GenAI engineer based in Thailand, working with a Forward Deployed Engineer mindset.
I completed a Master’s Degree in Information and Communications Technology at the Asian Institute of Technology (GPA 3.0/4) and hold a Bachelor of Technology in Computer Science from JNTUH College of Engineering, Hyderabad (GPA 8.8/10).
Applied AI Work
My thesis focused on detection and canopy size estimation of oil palm trees using deep learning–based instance segmentation (YOLOv8, YOLOv11, SAM) on multi-GSD UAV imagery. I deployed the best-performing model weights as an AI Teacher Agent, reducing manual annotation time by more than 80%.
I also build agentic systems for operational triage, institutional memory, research workflows, and local-first speech coaching. My focus is taking ambiguous needs through experimentation, deployment, and measurable outcomes.
What I Work With
- Applied AI, GenAI & Agents — LangChain, LangGraph, RAG, multi-agent orchestration, prompt engineering, LLMOps
- Computer Vision — YOLOv8/v11, SAM, Mask R-CNN, instance and semantic segmentation, OpenCV
- ML/DL Stack — Python, PyTorch, HuggingFace, ONNX, Scikit-learn
- Cloud, MLOps & Edge AI — AWS SageMaker and Bedrock, model deployment, quantization, edge inference
- Geospatial AI — UAV imagery, spatial intelligence, geospatial data pipelines, multi-GSD analysis
- Languages & Tools — TypeScript/JavaScript, Docker, Git/GitHub, Jupyter, LaTeX
Beyond the Screen
I’m an IPF-registered competitive powerlifter under TAAP/IPF. In 2025, I competed in both NQ1 (March) and NQ3 (November) in the U74kg Men’s Raw Open category — totaling 390 kg and 430 kg respectively, placing 3rd in both events. I also serve as Head of Events for powerlifting at AIT.
I believe training the body is as important as training the mind.
What This Blog Is About
This is where I write about things I’m learning, building, and thinking about — Applied AI, GenAI, agentic systems, computer vision, Geospatial AI, and the intersection of research and real-world engineering. No frameworks, no fluff. Just pure HTML and CSS.