Open to AI engineering roles · Remote / open to relocation

Cristian Chiorescu

Forward-Deployed AI Engineer

I build agentic systems and AI developer tooling — then embed with teams to ship them into production.

Calgary, AB

01 / About

From builder to forward-deployed

I'm a forward-deployed AI engineer. Most recently I was embedded on the AI Business Transformation team at Volaris Group (an operating group of Constellation Software), doing two things at once: building the agentic systems and tooling that make AI production-ready, and getting real teams to actually adopt them — autonomous multi-agent dev pipelines, MCP (Model Context Protocol) integrations, internal AI developer tooling, and running the developer track of an enterprise “AI Accelerator” across a 240+ company software portfolio.

“Forward-deployed” is the part I care about: being in the room where the AI meets the messy real system and the people who have to trust it.

I came to it the long way — self-taught, first as an e-commerce founder, then full-stack (Next.js / React / TypeScript), before going deep on agentic AI over the last year. Calgary-based, open to remote or relocation.

Impact

100+: developers guided across 50+ software businesses
4: in-person AI Accelerators — Denver · Oxford · Toronto · London
10–15: embedded AI coaches led per event (Volaris, Microsoft, AWS)
months → a week: teams shipping in a week what used to take months

02 / Selected work

Independent AI projects

AI · Agentic Systems

Live

machinist

One-paragraph request → adversarially reviewed, tested PR

A GitHub-native multi-agent pipeline: a spec flow files a validated issue, and one approval label later an implementer, four specialist reviewers, an adversarial challenger, a fixer, and a deterministic test gate take it to a ready-for-review pull request — autonomously, in a Docker sandbox on GitHub Actions. Labels are the state machine; issue threads are the audit trail.

Multi-agentClaude CodePythonGitHub ActionsDocker

Code Case study

AI · Environmental Intelligence

Live

EnviroLens

AI-powered environmental intelligence

A full-stack platform that pairs live Calgary air-quality data with an OpenAI compliance assistant aware of current conditions — surfacing the right institutional knowledge at the moment a decision gets made.

Next.jsOpenAITypeScriptRecharts

Live Code Case study

AI · Developer Tooling

Live

gitvaluation

LLM-powered code & PR analysis

Point it at any GitHub repo: it pulls recent merged PRs, runs the diffs through an LLM with a structured-output prompt, and returns per-contributor impact analysis — confidence, complexity, and net code value. A demo of GitHub API integration, prompt engineering, and JSON-mode structured output.

Next.jsOpenAI (JSON mode)GitHub APITypeScript

Live Code Case study

Other workearlier full-stack & data projects

Field Operations Monitor

Real-time operations dashboard turning Open-Meteo data into a per-site safety index, with a resilient data layer and clean, responsive UI.

Next.jsTypeScriptOpen-Meteo API

BlushBowl

Recipe-discovery platform with shareable filters, built on TanStack Query and Zod-validated data.

Next.jsTanStack QueryZod

Stock Dashboard

Live-markets dashboard with Chart.js visualizations and a resilient multi-provider serverless data layer.

ReactNode.jsChart.js

03 / Skills

What I work with

AI & Agentic Systems

Claude / Claude Code
Model Context Protocol (MCP)
Multi-agent pipelines
LLM integration
Agentic dev tooling
Prompt engineering
Playwright MCP
AI-driven automation

Languages

Python
TypeScript
JavaScript (ES6+)

Frontend

React
Next.js
Tailwind CSS
shadcn/ui

Backend & Data

Node.js
REST APIs
Serverless functions
PostgreSQL
TanStack Query
Zod

Infrastructure & DevOps

Azure
Azure Kubernetes Service (AKS)
Docker
Kubernetes
CI/CD (GitHub Actions)
SAST & container scanning
Observability

Cloud

Azure
AWS (familiar)

04 / Contact

Let's build something

I'm looking for forward-deployed / AI engineering roles where I can build agentic systems and help teams adopt them. If that sounds like your team, I'd love to talk.

cristian@cristianchiorescu.com

LinkedIn GitHub Résumé