I’m based in Tokyo, Japan and work mainly across AI, full-stack development, SaaS, automation, mobile apps, and product development. I also have access to active development teams and individual engineers here in Japan. So depending on the project, can support either a specific technical area or a full development process. First, big thanks to the ADMIN for building this community. Really appreciate the work behind it. Happy to be here, and happy to contribute where I can. Most of my work is with global clients, usually founders or companies building something with a real vision behind it. Not really looking for one-off tasks only. I prefer working with people who want to build, improve, launch, and keep growing a product over time. - Main areas I work in: • AI agents and multi-agent systems • LLM apps, RAG, AI search, knowledge systems • Business automation and internal AI tools • SaaS platforms • Web applications • Mobile apps • CRM and booking systems • Marketplace and matching platforms • Logistics and dispatch systems • GIS and location-based apps • AI customer support systems • Data processing and analytics • Recommendation systems • API integrations • Cloud infrastructure and scaling - Typical tech stack: Frontend: React, Next.js, TypeScript, JavaScript, Tailwind Backend: Python, FastAPI, Node.js, Express, Golang, REST, GraphQL, gRPC AI / ML: PyTorch, TensorFlow, Hugging Face, LLMs, RAG, vector databases, AI agents, NLP, computer vision Mobile: React Native, Flutter, Swift, Kotlin Database: PostgreSQL, MySQL, MongoDB, Redis, Pinecone, FAISS, Elasticsearch Cloud / DevOps: AWS, GCP, Azure, Docker, Kubernetes, CI/CD, GPU systems - Have worked across quite a few industries too. Healthcare, logistics, hospitality, education, finance, e-commerce, media, marketplaces, SaaS, customer support, field services, and more. - I can also help with: • Product planning • Technical architecture • MVP development • Production development • AI product strategy • Workflow design

I’m a Senior AI and Data Automation Engineer with strong experience building AI-powered applications, data pipelines, and automation systems that solve real business problems. My core strength is connecting AI, data, APIs, and business workflows into reliable end-to-end solutions. I work with Python, SQL, LLMs, APIs, cloud platforms, and automation tools to build systems that reduce manual work, improve data quality, and make processes more efficient. I also have experience leading a team of five engineers, where I focus on technical direction, problem-solving, code quality, and delivering projects reliably. I’m comfortable taking ownership from architecture and development through testing, deployment, monitoring, and ongoing improvement. I enjoy turning complex requirements into simple, scalable, and practical solutions that create measurable value for the business.

Every site with one of those 3D product renders you can spin looks like it cost money. This is the skill that gets you there from a single photo. It is the last of the four in my design skills video this week. https://github.com/img2threejs/img2threejs You give it one reference image of an object. It hands back a Three.js model written as TypeScript, built from primitives and procedural shaders. Not a mesh file and nothing downloaded. Plain code you can edit. Small enough to drop straight into a site and already set up to animate. It does not try to get there in one go. It builds in passes: a rough blockout first, then structure, form, materials, surface and lighting. After each pass it renders the model, compares it with your photo and fixes what missed. The comparing and gating is done by plain Python scripts, so the model only spends tokens on looking and on writing code. I ran it on a coffee machine photo on camera. The first pass was rough and I said so. It kept re-rendering while I was talking. I showed a second one I had generated earlier to give an idea of where it gets to. What I have found is that a clean photo on a white background with not too many moving parts works well. A busy image just gives it more to get wrong. Install: git clone https://github.com/img2threejs/img2threejs.git ~/.claude/skills/img2threejs Or paste the repo link into Claude Code and ask it to install the skill, which is what I did in the video. Then attach your image and run: /img2threejs Rebuild this object as a Three.js model, keep the proportions, angles and colours. It runs in Codex and OpenCode too from the same skill folder. 16,000 stars, Apache 2.0. The live gallery at img2threejs.io is worth a look, because every model on it is generated code running in your browser. What is the one product on your site you would rebuild in 3D first?