projects
Nine systems, all shipped.
On-device LLM inference, RAG pipelines, multi-agent systems and the MLOps that keeps them honest — each with a write-up of the problem, how it works, and why it exists.
Kotlin · LLaMA · GGUF
PrometheusAI — Offline LLM assistant for Android
On-device inference with zero cloud dependency. Runs LLaMA 3.1, IBM Granite, and Mistral via 4-bit GGUF at ~8 tok/s, with on-device RAG over your own documents.
Python · LLM · Compression
tokenash — Local-first context compression
Context compression for LLM applications that runs locally — 50–90% fewer tokens for the same answers, with nothing shipped to a third-party service to get there.
Python · Research · State-Space
HLST — Long-context LLMs on edge
Reference code for my TechRxiv preprint: hierarchical latent state-space recurrence that democratises long-context LLMs on edge devices, as a transformer alternative.
Python · Kubernetes · vLLM
KCD New York 2026 — Production RAG on Kubernetes
Demo from my KCD New York 2026 talk — deploying, autoscaling, and observing production RAG pipelines on Kubernetes with vLLM and vector search.
Python · Apache Beam · LLM
Apache Beam Summit 2026 — Real-time AI pipelines
Embedding LLMs and RAG directly into Apache Beam transforms for low-latency inference on high-velocity data streams.
Python · Agents · Automation
Relay — Open-source outbound agent
An open-source AI agent for outbound leads — the research, qualification, and follow-up loop handled by a tool-using agent rather than a sequence of manual steps.
Rust · LLM · Notes
Franola — Open-source AI note-taking
An open-source AI note-taking app in the Granola mould, written in Rust — meeting notes captured and structured by a model, without the notes leaving a proprietary product.
JavaScript · Agents · Finance
GateKeep — Agentic personal finance
An agentic-AI finance tracker that ingests transactions and reasons over them with tool-using agents to surface spend insights.
Python · NLP · Perplexity
AIORNOR — AI-or-human text detection
Detects whether a piece of text is AI-generated or human-written using a perplexity-based metric, served through a lightweight web app.
Hiring for AI or ML?
I am open to AI/ML Engineering, Data Science, and Python roles, plus research collaborations and consulting. New York based, shipping worldwide.