Maxime Guillemin — Quick View

A linear, scrollable version of this portfolio — no windows, no drag-and-drop. For the full desktop experience, switch back anytime.

← Back to desktop

About

AI-Augmented Full Stack Developer — TypeScript, React, Next.js, NestJS, and increasingly, agentic tools like Claude Code as part of the actual build process.

I'm Maxime, a full stack developer who builds with AI as a core part of the workflow, not an afterthought. This site is itself a case in point: designed, coded, and shipped in a two-week sprint with Claude.

Open to opportunities in France and internationally, with a particular interest in the Canadian tech market.

Kind
Full Stack Developer
Created
July 2025
Where
Clermont-Ferrand, France
Comments
AI-Augmented Full Stack Developer

Education

  • Baccalauréat, Scientific track (2019)
  • La Capsule — Coding Bootcamp, RNCP Level 6 (2023)
  • Epitech Lyon — MSc Pro, Software Engineering (2025)

Background

  1. 2023

    Completed an intensive coding bootcamp at La Capsule, earning a state-recognized RNCP Level 6 qualification.

  2. October 2023 – September 2024

    Full-stack developer (work-study) at Les Biens en Commun, a Lyon-based startup renting everyday equipment through connected lockers. Worked across the front end, back end, and database layer, and wrote Bash scripts to manage the connected locker systems. Helped set up and launch locker installations on-site early on, later handling deployment remotely. As one of two developers in the company, contributed directly to technical decisions and resolved production incidents affecting the user experience.

  3. 2023–2025

    Pursued a professional Master's (MSc Pro) at Epitech Lyon, deepening full-stack and software architecture skills.

  4. July 2025

    Graduated from Epitech Lyon.

  5. Present

    Building this portfolio and two side projects (an MCP server, a multi-agent trading bot) to demonstrate hands-on, AI-augmented development.

Projects

Augmented GitHub MCP Server

An MCP server that gives Claude AI-powered PR review and live cost tracking on top of GitHub.

Developer Tool · Planned

Problem

Reviewing pull requests well takes time, and calling the Claude API to help doesn't come with built-in spend guardrails. There's no lightweight way to get AI-assisted PR feedback inside GitHub while keeping token usage and cost visible and bounded.

Approach

A custom TypeScript MCP server that extends GitHub workflows with two capabilities: an AI reviewer that reads pull request diffs and suggests concrete improvements, and a cost-tracking layer that logs Claude API token usage per call and enforces a budget. Built as a standalone MCP server so it plugs into Claude Code or any MCP-compatible client, not tied to one IDE.

Status

Not started yet. Development is planned as a focused ~1-month build once the portfolio ships.

Stack

  • TypeScript
  • Node.js
  • Model Context Protocol
  • GitHub API
  • Claude API

Multi-Agent Paper Trading Bot

A multi-agent trading system using Claude and a retrieval layer to reason about paper trades on live market data.

Trading Application · Planned

Problem

Most trading bots follow rigid, hand-coded rules and can't explain their reasoning. Testing a more adaptive, LLM-driven strategy safely requires a paper-trading environment where agents can reason, retrieve context, and act without risking real capital.

Approach

A NestJS backend orchestrates specialized agents (market analysis, risk, execution) built on the Claude API, backed by a Next.js dashboard. Trades run against Alpaca's paper trading API, and a RAG layer (PostgreSQL with pgvector) gives the agents relevant historical context before each decision.

Status

Stack decided, no code written yet. Development has not started.

Stack

  • NestJS
  • Next.js
  • Alpaca API
  • Claude API
  • PostgreSQL
  • pgvector

Contact