AI Full-Stack Engineer — Founding Team

Job Description

About Us:
We are a Canada-based AI studio with a diverse portfolio of eight production products across various domains, including SaaS, immigration technology, municipal software, web auditing, quantitative finance, and consumer AI. Our entire infrastructure operates on Google Cloud Platform (GCP) using services like Cloud Run, Vertex AI, and Gemini. We are seeking one talented engineer to build, ship, and maintain our product offerings.
Role Overview:
This position is part of the founding team, which means you'll work directly with the founder without the distractions of project managers, daily standups, or additional layers of bureaucracy. You'll receive detailed specifications and have the freedom to execute your work.
What You'll Build:

Agentic AI workflows, including LangGraph, multi-agent orchestration, and retrieval pipelines.
Vertex AI Search and Agents with 13 production builds (RAG, grounded generation, cite-or-silence).
Backend services using FastAPI, Cloud Run, PostgreSQL, and Google Cloud Storage (GCS).
Frontend applications with 14 (App Router) and Prisma ORM.
Infrastructure management including GCP IAM, Cloud Build, service accounts, and cost optimization.
AI evaluation and testing using pytest gates, adversarial QA, and hallucination detection.

Day-to-Day Responsibilities:

Start with a detailed build specification, ship the solution, run the test suite, and deploy.
Remediate issues by fixing regressions across LangGraph workflows, Vertex AI builds, and frontend applications.
Build and maintain RAG pipelines, incorporating cite-or-silence grounding.
Optimize costs, managing GCP credits, model cost caps, and budget tuning.
Work across different repositories, switching contexts between Python backends, frontends, and AI agent architectures.

Our Tech Stack:

Python/FastAPI: The backbone across six ventures.
GCP: Utilizing Cloud Run, Vertex AI (Search and Agents), GCS, Cloud SQL, and Cloud Build.
14 (App Router) + Prisma: Our standard for frontend development.
PostgreSQL: The core data layer for our applications.
Gemini 3.1 Pro: Used for reasoning, whole-codebase audits, and offering 1M context windows.
LangGraph/LangChain: For agentic workflows and multi-agent orchestration.
Additional Tools: Firebase Auth, Temporal, Twilio, and n8n are used in specific ventures.

You Are:

Proficient in Python and FastAPI—this is a non-negotiable requirement, as six out of our eight ventures rely on a Python backend.
Familiar with GCP, specifically Cloud Run, Vertex AI, and GCS.
Comfortable working with LLM APIs such as Gemini, OpenAI, and LangChain/LangGraph.
Capable of reading dense specifications and executing without extensive guidance.
Committed to code quality, testing before pushing changes and auditing before deployment.
A clear and effective async communicator—our team spans different time zones, making thorough documentation essential.

Big Plus:

Experience with Vertex AI Search and Agents.
Familiarity with RAG pipelines (indexing, retrieval, grounded generation).
Knowledge of Firebase Auth, Twilio, Temporal, or n8n.
Contributions to open-source projects or personal side projects.

What You'll Get:

Equity range of 2-5% across ventures (4-year vesting with a 1-year cliff) plus profit-sharing.
A small monthly stipend, as this is primarily an equity-focused role.
Direct mentorship from a founder actively shipping production AI on GCP.
Hands-on experience with eight live products in your portfolio, providing better exposure than a typical boot camp or internship.
Fully remote, asynchronous-first work environment.

How to Apply:
Please provide one of the following to apply:

Your GitHub profile showcasing something you've built.
A 2-minute Loom video walking through a project.
A link to a deployed side project.

Resumes alone will not be sufficient; we want to see what you've created.