01 / Data engineering / AI

production

Production data pipelines

I led the team and co-developed an automated pipeline turning heavily unstructured, inconsistent inputs into standardized business data.

The system combines AI methods with local GPU compute, automated runs, observability, and provenance. Storage and processing were designed to avoid unnecessary reprocessing and wasted compute.

02 / LLM systems / technical leadership

production

Persistent multi-agent systems

I led the team building a multi-site, multi-agent LLM chatbot with continuous memory and presence, taking responsibility for technical decisions and prototypes.

The work connected multiple products and agents into a production system. My role combined architecture, hands-on prototyping, and engineering leadership.

03 / Hardware / AI infrastructure

internal use

GPU experimentation lab

I built a GPU cluster for an AI engineering team's experiments and managed and administered the hardware.

This included the physical compute environment behind the team's model work, alongside responsibility for the systems running on it.

04 / Independent venture / applied R&D

in development

AI software across heterogeneous hardware

At aleph0, we are developing low-level software for AI on heterogeneous hardware, especially at the edge.

The work combines hardware-specific compiled models, a single-binary runtime, and custom model optimization for compatibility and lower power use. It is intended for open source and has no users yet.

Further work includes co-developing an automated LinkedIn marketing tool with topic suggestions and tone adaptation, writing technical articles, and delivering workshops on AI, LLMs for software engineering, and safety practices.

Published work in medical imaging, phototoxicity prediction, and LLM routing is collected under research.