About this role
Gigi is hiring an AI Agent Engineer in Toronto to own the end-to-end development of the agents and workflows powering their enterprise media buying platform. This role suits a hands-on software engineer with experience building applications using large language models who wants to shape core product capabilities.
Role Overview
Gigi operates an agentic operating system for enterprise media buying, featuring an AI media manager for Amazon DSP. Located in Toronto, the engineering team functions in an in-office environment with flexibility to work remotely on Wednesdays. The position centers on designing reliable software systems where LLMs reason, utilize tools, manage context, and execute customer actions.
Key Responsibilities
Requirements
Nice to Have
Skills and Tools
Salary and Benefits
About the Company
Gigi is the agentic operating system for enterprise media buying, backed by investors Golden Ventures and Aperiam Ventures. The founding team brings over 15 years of experience building in Amazon Ads and ecommerce, including a prior exit exceeding $100 million.
How to Apply
Apply on the official company careers page to submit your application for the AI Agent Engineer position.
Skills and tech stack
Questions candidates ask
Where is the job located?
The role is based in Toronto with an in-office culture downtown and the option to work where you are most productive on Wednesdays.
What is the salary range for this role?
The base salary ranges from $110k to $200k, depending on experience level, alongside meaningful equity.
Do I need years of professional LLM experience to apply?
No, you do not need years of professional LLM experience or an AI research background, but you do need hands-on experience building with LLMs or agents through work, open source, or personal projects.
What technology stack does the company use?
The engineering stack includes Python, FastAPI, LangGraph, LangChain, TypeScript, Vue, Nuxt, Java, Spring Boot, PostgreSQL, pgvector, Redis, NATS, and AWS, alongside AI coding tools like Codex, Claude Code, and Cursor.
Will I work directly with customers?
Yes, engineers sit in on customer calls, read transcripts, and take feedback directly from media buyers to turn ambiguous problems into shipped product features.