Applied AI & GenAI Engineer | Agentic Systems · LangChain · LLM Apps | Computer Vision & Geospatial ML
M.Eng. in ICT — Asian Institute of Technology, Thailand

I’m an applied AI engineer who ships LLM and Agent‑powered systems end‑to‑end — from research ideas to working products.

My background is in AI & Computer vision. At AIT, my thesis on oil palm instance segmentation across 8 UAV altitudes reached 0.77 mIoU and cut annotation time by 80% via an AI Teacher Agent that auto‑labels new data — a practical agentic workflow for image processing.

Recent focus: agentic AI systems that are auditable and constrained, edge vision models under strict latency and power budgets, efficient training of LLMs and small models, and local-first tools for knowledge work.

Open to AI Engineer roles.

🔭  Building       : Cost-aware agent orchestration, self-organizing memory graphs, real-time coaching systems
🌱  Deepening      : LangChain / LangGraph agentic design patterns, context & harness engineering
🔐  Studying       : Offensive/defensive security fundamentals, applied to agent guardrails
🎨  Also learning  : Manim, for turning technical ideas into visual explanations

Real-time teleprompter and rehearsal coach for sales teams with local-first inference.

• Website: Live

Self-organizing memory graph that makes agent runs cheaper over time instead of just adding more context tokens.

• Website: Live

Agentic routing system that sends each support ticket to the cheapest capable model tier while holding accuracy steady.

• Website: Live

Multi-agent orchestration system with 9 specialized agents, 6 immutable writing laws, and 90% confidence gate for hallucination control. Built during thesis at AIT to automate research documentation and inference.

• Repo: Thesis-Agent-Kit

Reproduced OpenAI's Parameter Golf challenge: H100 training on RunPod with torchrun, FineWeb dataset, and continuous val_bpb tracking. Focus on reproducibility under strict wall-clock constraints.

• Demonstrates large-scale training orchestration and compute efficiency
• Repo: OpenAI-Parameter-Golf

Image-to-text retrieval on XR2 Gen 2 proxy (edge device). Achieved Recall@10 ≈ 0.73.

• Full pipeline: model selection, ONNX export, hardware profiling, dataset curation, inference optimization
• Demonstrates end-to-end edge ML deployment

Detection, counting, and canopy biometry of individual oil palms from UAV imagery at multiple ground sample distances (0.03–0.20m).

• Multi-model comparison: YOLOv8, YOLOv11, Mask R-CNN, SAM hybrids
• Metrics: precision, recall, F1, IoU, crown geometry errors across 8 altitude levels
• Agent-in-the-loop annotation (80% labeling time reduction) + generative tiling for synthetic multi-altitude data

• Roles where I ship agent systems directly alongside the teams that will run them, not just prototypes handed off after the fact
• Deepening context and harness engineering practice: getting more out of pretrained models through better system design, not bigger models
• Building a track record of small, measurable case studies (cost reduced, time saved, accuracy held) rather than open-ended demos
• Contributing to how agent memory and guardrails get evaluated as production concerns, not afterthoughts