I build the GenAI systems your product needs.
RAG, agents, and the infra to run them.
Fractional AI lead and hands-on build partner for founders shipping GenAI features, not just prototyping them.
Work With Me
Fractional AI Lead
Embedded 1–2 days/week as the GenAI decision-maker — architecture, build oversight, team upskilling. For teams past prototype who need someone to own it.
Let's talk →RAG / Agent Build
Ship a specific RAG pipeline or agent workflow end-to-end, scoped and priced upfront. Best fit for a defined feature with a clear success criterion.
Let's talk →LLM Integration
Get an LLM feature from spike to production — evaluation, guardrails, cost/latency tuning, the parts that don't show up in a demo.
Let's talk →GenAI Architecture Review
A short, paid engagement: audit an existing GenAI system, deliver a written assessment and prioritized fix list. Low-commitment way to start.
Let's talk →Projects
CPI Business
Hub71 Impact
MYOP Product Catalogue
Writing
VIEW ALL
Context is the hard part, and nobody sets out to build it
Why the same AI feature works at one company and fails at another: canonical definitions, current signals, and quality enforcement — the layers nobody budgets for.
The most expensive call is the one that fails after trying hardest
In a step-billed system your costliest interactions are the ones the model works hardest on and still can't finish. The effort paradox, and the four controls that bound it.
What an LLM feature actually costs to run
Cost is steps times tokens times retries, the failures dominate, and the pilot will not show you. The four buckets to model and the levers that actually move the bill.
Where AI belongs in your architecture — and where it doesn't
Models at the edges, deterministic code in the core. The patterns that don't need a model, the ones where it earns its keep, and the question to ask before adding it.
What does it mean
to be a Software Engineer
in the age of AI?
Agency
to make critical decisions
Human supervision is going to be critical for maintaining security and reliability of systems. It's not only just a regulatory requirement, but also for strengthening the systems to protect the business from adversaries.
What it means to be
a Software Engineer
in the age of AI
Knowledge
to keep the system running
Making sure the software is built the way it should be is important. When a technical problem arises, there needs to be someone who can take ownership and responsibility, to figure out and fix till it's completely mitigated.
What it means to be
a Software Engineer
in the age of AIStrength
of a team for a single Engineer
Building software has never been easier. But to do that properly, well-versed planning and proper execution is required as ever. With deep knowledge in software systems, a single engineer does an entire team's work utilizing AI the right way.
What it means to be
a Software Engineer
in the age of AI
Meet
The
