Principal AI Architect
Principal AI Architect working across agentic systems, RAG, knowledge architecture, evaluation, guardrails, and production deployment.
11 years across software, ML and AI — from regulated enterprise systems at Credit Suisse to production agentic systems today.
Selected work
01
Career guidance inside an enterprise has to combine employee context with internal knowledge while keeping AI behavior constrained enough for employee-facing use.
02
Federal criminal-defense drafting depends on hierarchical legal sources, accurate retrieval, and clear linkage between arguments and the material supporting them.
03
Generating marketing assets is easy; identifying the right personas and angles for a product before generation is the harder part.
04
Unstructured documents needed to be converted into structured knowledge, but the entities and relationships to extract changed depending on the ontology defined for each use case.
05
Investors needed useful summaries and signals about individual crypto projects from very large volumes of noisy Telegram and social-media data.
About
I started my career at Credit Suisse, working on production ML and data systems in a regulated environment. I later moved into freelance work, designing and building AI systems for companies that need them to hold up beyond the prototype stage.
I have followed that stack as it evolved — from classical ML and NLP into LLMs and agentic systems. Today I help enterprises deploy agents reliably in production, with evaluation harnesses and monitoring.
Credentials
Contact
I work with teams building production AI systems where architecture, reliability, retrieval, evaluation or agent behavior actually matter.