Software Engineer - AI Agents

About Magical

Magical is an agentic automation platform transforming healthcare with state-of-the-art AI—delivering AI agents that work in real production environments.

We believe the future of healthcare will be shaped not by replacing people, but by amplifying their talents. Magical empowers healthcare organizations to scale their top experts across every workflow, driving greater accuracy, efficiency, and care throughout operations.

Our “AI employees” automate repetitive, time-consuming workflows while keeping people in control. We focus on healthcare—a $4 trillion industry overwhelmed by administrative complexity—automating critical processes like prior authorizations and medical coding, so providers can focus more on patient care.

Our Traction

• Customers are expanding from initial workflows into broader use cases after seeing reliable production results
• 7-day proof-of-concept projects demonstrate real value quickly, where months are typical in the industry
• Our self-healing automations deliver production-grade reliability at scale
• Magical is backed by Greylock, Coatue, and Lightspeed, with $41M raised. Our founder, Harpaul Sambhi, previously sold his first company to LinkedIn.

About the Role

As a Software Engineer, you’ll build the systems powering Magical’s AI agents. This is a wide-funnel role, open to a range of experience levels and backgrounds. We’ll calibrate scope according to your skills, but we’re looking for people eager to own meaningful work, learn quickly, and help us ship robust products.

Under the hood, Magical orchestrates long-running, high-stakes healthcare workflows involving queues, run state, browser automation, model calls, evaluations, observability, and human-in-the-loop recovery.

You’ll help convert messy customer inputs—SOPs, decision trees, portal behaviors, edge cases—into reliable automations. You’ll design systems that draft workflows, test them, catch failures, recommend edits, and escalate to humans as needed. You’ll also work on runtime reliability, workflow pathways, evaluations, and specialized agents for repeatable healthcare tasks.

This is a hybrid role based in our Toronto office.

What You’ll Do

• Design and build backend and full-stack systems for AI agents and healthcare automations
• Own projects from implementation through deployment, monitoring, and iteration
• Build product and platform features for automation creation, workflow pathways, testing, editing, and production run reporting
• Improve reliability with better run state management, queues, error classification, alerts, and dashboards
• Collaborate with product, design, and deployment engineering to turn real healthcare workflows into robust automation systems

You May Be a Fit If

• You’ve built backend or full-stack systems running in production
• You have strong fundamentals across databases, APIs, queues, async workflows, and observability
• You’re comfortable working in TypeScript/Node or a similar backend stack
• You’ve integrated AI tools into your developer workflow and enjoy experimenting with new approaches
• You favor action—shipping, learning, prioritizing, and iterating quickly
• You take ownership of your work and enjoy helping teammates grow

Even Better If

• Experience building platform, infrastructure, or workflow systems
• Experience creating agentic products or agent-based workflows
• Experience integrating LLMs or AI models into production backend systems
• Background in event-driven architectures, workflow engines, observability, or runtime reliability
• Experience in healthcare operations or revenue cycle management

We’re building the best self-serve agentic automation platform for healthcare, and we’re just getting started. Come join us.