Principal AI Engineer

I build AI systems that
earn autonomy.

Production LLM systems for agentic workflows, retrieval, evals, and progressive automation — built around real workflows, explicit trust, and measurable delegation.

  • 50+ AI products shipped
  • 150M+ User scale
  • ~$20M Revenue impact

I do not resist automation. I sequence it.

Open to Principal / Staff AI Engineering roles and selective consulting · remote · EU/CET

Approach

Automation matures from real work.

I start by mapping how work actually happens — decisions, handoffs, exceptions, shortcuts, failure modes. I make state and trust explicit. Then I automate the parts that have earned enough evidence to be safely delegated.

The goal is not permanent control. It is a system where control can be safely transferred.

01

Map the real flow

The truth is in how work already happens, not in the spec.

02

Make trust explicit

State, evidence, evals, traces, permissions, and fallback behavior.

03

Delegate as evidence accumulates

Automation expands only where quality is measurable.

Capabilities

What I build

Agentic workflow systems

State machines, tool contracts, approvals, recovery paths.

Trust-critical retrieval

Grounding, permissions, citations, calibrated uncertainty.

Evaluation & observability

Traces, regression gates, delegation criteria.

Progressive automation

Manual → assisted → bounded delegation → trusted automation.

Selected work

Across these projects, the pattern is the same: make the flow explicit, define trust boundaries, add evaluation, and automate progressively.

Method

How autonomy is earned

  1. 01

    Observe

    Capture how work actually happens.

  2. 02

    Structure

    Make state, decisions, handoffs, and risks explicit.

  3. 03

    Assist

    Reduce operator friction without hiding responsibility.

  4. 04

    Delegate

    Automate bounded steps where quality is measurable.

  5. 05

    Raise

    Humans move from execution to direction and system design.

Position

What I believe

Five working theses behind the systems I build.

  1. The real workflow is the source of truth.

    Most AI systems are designed against an idealized version of the work, not how it actually happens. The cost shows up in the second iteration, not the demo.

  2. Human-in-the-loop is a stage, not an architecture.

    Teams that treat HITL as the destination keep humans clicking approve forever. The point is to move them up the stack.

  3. Evals are not QA.

    They are the mechanism by which a system earns its next level of autonomy. Treating evals as a quality gate underuses them.

  4. Trust is not a feeling. It is a measurable property.

    State, uncertainty, evidence, and failure modes either exist explicitly in the system, or they show up later as production risk.

  5. Automation is the outcome, not the starting point.

    Production AI matures: observe → assist → delegate → trusted automation. Skipping stages is one of the most common ways production AI systems fail.

Current work

Current work

  1. Building — Exocortex

    A personal OS for knowledge work: one intake, one command surface, structured memory, and progressive automation. The same thesis I apply professionally, applied to my own workflow.

    exocore.cx →
  2. Thinking — Engine vs Bolt-on

    Why the real frontier in AI for learning is the delivery loop — not a chatbot beside static content.

    Read essay →
Work with me

Work with me

If you're building AI inside real product workflows — agents, retrieval, evals, observability, or progressive automation — I'm open to Principal / Staff AI engineering roles and selective technical collaboration.

Remote-first · Europe / CET-friendly · hands-on architecture and delivery.