01
ai-chat
Self-hosted coding companion on vLLM with streaming, workspace tools, agent harness, and voice.
View projectJoseph Kaiser
Self-hosted systems, model experiments, and web apps.
I spend most of my time coding, building self-hosted systems and experimenting with small machine learning models. Lately that means maximizing the capabilities of my limited hardware stack with clever methods.
Background in finance, engineering and philosophy. Increasingly focused on software engineering and AI/ML research.
Projects
Selected work.
02
myrssfeed
Self-hosted RSS reader on a Raspberry Pi — feed scoring, theme labeling, newsletter ingestion, and a web UI that stays out of the way.
View project03
Current focus
Full fine-tuning SmolLM2-1.7B on AddSub math problems. Learning rate sweeps, loss masking ablations, and data scaling experiments on a single 4090.
In progress
Philosophy
What I keep building toward.
I want to build systems that are useful at real scale: fast, efficient, and enjoyable to operate. Good software should create leverage for the user, abstract unnecessary pain, and still stay legible underneath.
01
UNIX sensibility
UNIX still feels like the right design language: small parts, clear interfaces, and systems that stay composable instead of collapsing into mystery. That mindset shapes how I configure local Linux servers, repurpose used hardware for new workloads, and turn an old gaming PC with a newer GPU into something genuinely useful.
02
AI systems
The work centers on pushing AI systems as far as they can go — then designing interfaces that keep a human at the end of every decision loop. Borrow from military command philosophy: automate everything except the judgment call.
03
Performance and operation
I care about software that is fast, efficient, and dependable in practice, not just impressive in a demo. The goal is to build tools that respect operator time, make good use of available compute, and surface the right abstraction layer so people can move quickly without losing control of the system.
Tools
Technology Stack
I prefer technologies that stay legible under load, do not punish small-scale deployment, and let me move from experiment to usable software without a lot of excess ceremony.
Languages
- Bash
- C
- Python
- HTML
- CSS
- JavaScript
- TypeScript
- SQL
Model Stack
- CUDA
- Hugging Face
- PyTorch
- vLLM
Applications
- Docker
- FastAPI
- Sqlite3
- Tailscale
Systems
- Linux
- Git
Contact
Let's connect.
If you like coding, self-hosted infrastructure, small-model research, or thoughtful software tools, I am always happy to compare notes.
Email is best: [email protected]