AI & ML Engineer — Production Agent Systems (Equity)

General Magic; Toronto; On-site; CAD 120,000 - 200,000; Full time

Benefits offered by this job

Equity

MacBook Pro

Onsite work in Toronto

Job summary

General Magic is building AI agents that handle quoting, follow-ups, document collection, verification, claims intake and broker communication, connected directly to carrier, MGA and broker systems. We work onsite in Toronto, offering equity, a new MacBook Pro and more.

You will design and build the AI core, including agentic and multi-agent systems, prompts, and evaluation pipelines. The role emphasizes fast, safe production deployments and collaboration across backend, APIs and data models to

Qualifications

• Deep understanding of how LLMs work beyond API usage.
• Experience building production agentic systems.
• Strong backend fundamentals and ability to move across codebases quickly.
• Experience treating evals and safety as core engineering practices.
• Drive to ship fast in a high-velocity environment.

Responsibilities

• Design and build agentic and multi-agent systems with tools, state and robust failure handling.
• Engineer prompts and context with guardrails to reduce hallucinations.
• Cut cost and latency with caching, context structuring and model selection.
• Build eval pipelines that catch regressions and tie quality to releases.
• Collaborate across backend, APIs and data models to ship features end-to-end.

Skills

LLM fundamentals

Agentic systems

Backend engineering

Eval & safety engineering

Ship fast mentality

Job description

General Magic is building AI agents that handle quoting, follow-ups, document collection, verification, claims intake and broker communication, connected directly to carrier, MGA and broker systems. We work onsite in Toronto, offering equity, a new MacBook Pro and more.

You will design and build the AI core, including agentic and multi-agent systems, prompts, and evaluation pipelines. The role emphasizes fast, safe production deployments and collaboration across backend, APIs and data models to