shanhui notes
applied ai (product) engineer, i usually write about building applied AI systems, learning hardware, and random musings about the changing nature of knowledge work
back in 2016, i first taught myself how to code so i can build personal web apps for myself and for my volunteer work. i was volunteering at the time at an NGO to teach mathematics to highschool kids in Cambodian villages in Kampong Cham and i built small JS …
to build a search engine requires many components and algorithms, however the 2 critical components are the search service and the indexer + crawlers. i have built several crawlers and indexes before for different use cases such as Chinese news articles and eCommerce product research, so i figured it would be …
this is part of the multi-part series on building a jobs search engine in Rust. in the first part i wrote about the mechanics of how vector similarity search with embeddings work. here i will discuss building background task queues using rust async primitives and some learnings.
the embeddings indexer …
starting around March 2026, the bottleneck in many software engineering teams have move to reviewing AI generated code instead of writing every line by hand.
ai coding harnesses have gotten much better since then and many of the common mistakes like missing imports, null pointers that reviewers need to look …
so since early 2025 (ancient history), i have work with Cursor almost every day for both client work and my side projects. although i have been testing out using pi agent with open models like deepseek v4, however the vast majority of my agentic use is still within Cursor. for …
3D modeling and CAD is an area of generative AI that i have been interested in for a few months. part of the reason is that i do part time consultation work with Chinese industrial battery factories to build the right batteries for specific markets needs like Singapore and LATAM …
so i am working on a LLM + hardware side project, a full stack voice AI assistant for my uncle’s takeout restaurant. the system is not an edge TTS stack connected to cloud inference API. no, we are running it all on the edge hardware (no need for internet connection …
i am currently an indie applied ml developer working on building applied AI products and contributing to open-source. i do some consulting work for manufacturing and supply chain firms who needs help deploying open AI models in their workflows.
i started out my career in Malaysia and Singapore working in a fast growing eCommerce and payments startup and then moved to the United States to work for a logistics growth stage startup for a few years before moving back to Asia. currently i spend my time learning to make hardware, integrating local LLMs into edge chips, and building niche vertical AI agents, visiting factories pretending to be a FDE, and writing for fun.
you can email me at shanhui@proton.me