Model capabilities & reasoning
Exploring the limits of Transformers, context, memory, reasoning, and dynamic computation through experiments in real tasks.
Eason Wang
Multi-role practitioner: AIE・SWE・SA・FDE in the AI era
Exploring models, agents, intelligent systems, and real-world engineering. This is where I keep research notes, public projects, and ideas worth writing down.
CURRENT WORK
Turn Advanced Intelligence into Reliable Operations.
Conduct research and engineering practices centering on agents, real-world business logic, and software systems.
Agent runtimes
Connecting model capabilities with planning, tools, permissions, memory, and validation so agents can reliably complete complex abstract tasks.
Industrial knowledge systems
Connecting engineering documents, asset entities, digital delivery, and business rules to turn scattered material into traceable, queryable industrial knowledge.
Intelligent systems architecture
Combining model serving, retrieval, workflows, data storage, evaluation, and observability into intelligent systems that can be deployed and maintained.
A PATH SO FAR
A path through learning,
research, and practice.
From algorithmic research to real-world industry applications, each step has been about turning understanding into systems that can be tested, used, and improved.
- 2021–2022
Starting with reinforcement learning
First encountered reinforcement learning and completed my undergraduate thesis with Q-learning.
- 2022–2023
Machine learning and research training
Studied classical machine learning methods systematically and began academic research.
- 2023–2024
Moving into LLMs and engineering
Contributed to a National Natural Science Foundation project, began working with LLMs, and entered engineering practice through an internship.
- 2024–2025
From research to building
Completed academic and graduate theses on time-series models, worked on LLM fine-tuning in real projects, and began building AI products independently.
- 2025–NOW
Bringing AI into real industries
Working full-time on applied AI in traditional industries, refining systems that can make a difference in real settings.
PUBLIC PROJECTS
Things taking shape on GitHub
01
AgentForSaaS
Enterprise Agent SaaS architecture and engineering practices distilled from production projects.
GO · AGENT SAAS · GITHUB ↗ 02LLM Zero to Agent
A record of the journey from LLM fundamentals to production-ready agent tools and their evolving technologies.
PYTHON · LLM / AGENT · GITHUB ↗ 03Industry Knowledge Base System
A practical blueprint for building industrial knowledge base systems, distilled from real projects.
GO · KNOWLEDGE SYSTEM · GITHUB ↗SELECTED NOTES