AI/ML Engineer

Who we are

For decades, insurance software has been built around rigid forms, portals and call centers that create friction for customers and slow teams down. Even as AI has advanced, most insurance work remains manual and spread across disconnected systems.

General Magic builds AI agents that handle quoting, customer service, underwriting, follow-ups and broker communication, connected directly to carrier, MGA and broker systems. We've raised $7.2M USD from Radical Ventures, a16z and several AI leaders.

We reward people who thrive with high autonomy, love shipping quickly and want real ownership. We work onsite in Toronto five days a week.

The role

You'll own the AI systems behind General Magic's products, from building and orchestrating agents to making sure they perform reliably in production.

We're looking for an AI Engineer who understands how LLMs work and can turn that understanding into products customers rely on. You'll design agent workflows, improve accuracy, reduce latency and costs, and build systems that can handle complex insurance tasks. We're a flat team where engineers own their work, challenge assumptions and help shape what gets built. You'll work directly with the founders and ship AI systems used by real customers.

In this role, you will

• Design, build and deploy AI agents and multi-agent systems that handle real insurance workflows

• Build reliable tool use, state management and error handling into agent workflows

• Engineer prompts and context to improve accuracy, reliability and consistency

• Develop evaluation pipelines that measure agent performance, catch regressions and improve quality with every release

• Optimize model performance, latency and costs through caching, context management and model selection

• Work across backend services, APIs and data models to bring AI features into production

• Ship to production frequently and take responsibility for how your systems perform for customers

For this role, you should have

• A strong understanding of how LLMs work, including their capabilities, limitations and underlying principles

• Experience building and deploying AI agents or LLM-powered systems in production

• Strong programming and backend engineering fundamentals

• Experience with prompt engineering, context management and tool calling

• Familiarity with AI evaluation frameworks, testing and reliability practices

• Ability to work independently, make technical decisions and own systems from start to finish

• Experience using AI coding tools such as Claude Code, Codex or similar

Experience with multi-agent architectures, model fine-tuning, inference optimization and large-scale AI deployments is a plus.

Compensation and benefits

• $130K–$220K CAD base salary, depending on experience, plus equity

• Health and dental benefits

• Wellness benefits

• Dinner covered when working in the office past 7:30 PM

• Expenses covered for conferences, tools and anything you need to do your job well

• Direct ownership of AI systems deployed to real customers

• Work alongside experienced operators, engineers and founders who care deeply about what they build