Hi! I'm AsterZephyr.
Algorithm Engineer. System Builder. AI Explorer.
Interested in
About Me
I'm an algorithm engineer at a leading digital marketing group, where I design and build real-time bidding systems, ML model serving pipelines, and budget optimization algorithms for programmatic advertising at scale. My day-to-day involves Go and TensorFlow Serving — turning ad auction math into production models that handle millions of bid requests.
On the side, I run an AI infrastructure project: an LLM API gateway aggregating 40+ model providers, a lightweight agent framework, and a service quality monitoring system built on real-token probing. I care about systems that actually work under load — not just demos.
My path: from search-ads-rec system architecture to algorithm research. Currently exploring LLM4Rec and unified sequence modeling for large-scale recommendation — where transformer architectures meet feature interaction in conversion prediction. I believe the best way to understand a system is to build it yourself.
Projects
Aster-HO
Agent Harness Observability — detect errors, context rot, and regressions in AI agent systems.
Aster-HO
AsterTypeless
A native macOS voice-to-text app — press Fn, speak, and polished text lands at your cursor in any app.
AsterTypeless
PolyAgent
A production-ready multi-agent platform with sandboxed execution, budget control, and observability.
PolyAgent
AI Daily Report Skill
A Claude Code skill that generates daily AI/tech intelligence reports from Hacker News and HuggingFace Papers.
AI Daily Report Skill
Excalidraw Skill
A Claude Code skill that generates importable Excalidraw architecture diagrams from source code.
Excalidraw Skill
Seata-Go
Latest Posts
从梯度下降到 Semantic ID：理解 RQ-VAE 所需的全部前序知识
一篇文章补齐从机器学习基础、深度学习、Transformer/LLM、搜广推系统架构到向量量化的全部知识链——读完后直接进入 RQ-VAE Semantic ID 训练那篇文章，不会有任何理解断裂。
码本利用率的骗局：RQ-VAE Semantic ID 训练的七个工程权衡
把码本向量维度改小，利用率飙到 90%+——这说明模型学好了吗？从码本崩塌到 Scaling Law，深入拆解 RQ-VAE Semantic ID 训练中的七个核心工程权衡。