Staff Software Engineer, AI

Build better healthcare together

Maple’s purpose is to meet the world's healthcare needs. We’re Canada's leading on-demand healthcare platform, connecting patients with Canadian-licensed doctors, nurse practitioners, and specialists. Today, we’re proud that over 8 million patients and 7,000 businesses and government partners have access to same-day, proactive, and ongoing care. We enable people to take control of their health and push the boundaries of what’s possible every day.

Bold minds. Big impact. A career at Maple is about making an impact. We empower bold thinking, surround you with an inspiring team, and are driven by a motivating purpose. Here, you’ll do work that changes lives—including your own.

The role

We’re looking for a Staff Software Engineer, AI to own and ship the next generation of AI-powered healthcare experiences at Maple.

You’ll work inside Product Engineering, partnering with Product, Design, Platform, Security, Privacy, and clinical experts to take ambiguous patient and provider problems from discovery to production. You’ll spend meaningful time designing, writing, reviewing, and operating production code for customer-facing AI capabilities. You’ll also help the wider engineering organization adopt the patterns that make those capabilities reliable, safe, observable, and cost-effective.

This is a hands-on, senior individual contributor role for an engineer who has spent the last few years actively building AI into real products—not just experimenting with models or defining high-level standards. You’ll have direct ownership of a high-impact product area while serving as a technical leader to influence how AI is built and scaled across Maple.

Your responsibilities

As a Staff AI Engineer, you will:

• Own a meaningful AI product area from problem discovery and technical design through implementation, launch, monitoring, and iteration.

• Partner with Product and Design to understand user needs, identify where AI creates real value, and turn ambiguous problems into simple, useful experiences.

• Design and build production AI systems using LLMs, agents, retrieval, tool calling, workflow orchestration, and human-in-the-loop patterns where appropriate.

• Write production code, review designs and pull requests, debug difficult issues, and participate in operational ownership after launch.

• Establish practical evaluation and monitoring approaches that measure product quality, safety, reliability, latency, and cost.

• Work with Platform Engineering to make the right decisions about shared services, model providers, infrastructure, and ownership boundaries.

• Help teams make sound trade-offs across user experience, clinical quality, privacy, security, reliability, and AI unit economics.

• Turn successful product implementations into reusable patterns that help other squads move faster and more safely.

• Mentor engineers and raise the technical bar through collaboration, design reviews, documentation, and example-setting.

• Partner with Security, Privacy, Legal, and Clinical stakeholders on responsible handling of PHI and safe deployment of AI capabilities.

• Communicate technical decisions and product trade-offs clearly to engineers, product leaders, executives, and cross-functional partners.

What success looks like

In your first 90 days, you’ll build context on Maple’s product, users, AI capabilities, and engineering environment. You’ll partner with a product squad to ship or materially advance one meaningful AI capability, establish a pragmatic evaluation and monitoring baseline for it, and build strong working relationships with Product, Design, Platform, Security, Privacy, and clinical partners. You’ll also identify opportunities to turn what you learn into reusable engineering patterns.

Over your first 12–18 months, you’ll demonstrate measurable product or workflow impact from the capability you helped ship and improve its quality, safety, reliability, latency, and cost through production learning. You’ll help multiple squads ship AI features that meet Maple’s standards for product quality, safety, observability, and cost. You’ll establish reusable approaches to evaluation, agent execution, monitoring, and operational readiness while staying close to users and product outcomes as your leverage increases across the organization.

What you bring

• 8+ years of experience building and operating production software, with Staff-level scope or equivalent technical leadership.

• Recent hands-on experience shipping AI- or LLM-powered product features as part of a product engineering team.

• Experience taking ambiguous product problems through technical discovery, architecture, implementation, launch, and iteration.

• Strong software engineering fundamentals and the ability to make pragmatic decisions across scalability, reliability, performance, security, and maintainability.

• Hands-on coding experience in a modern production language, with the ability to work across AI services and product systems.

• Experience designing APIs, data flows, services, integrations, or distributed systems that operate in production.

• A product mindset: you care about who uses what you build, what outcome it creates, and how it improves over time.

• Proven ability to influence technical direction across teams without relying on formal authority.

  Experience mentoring engineers and improving how teams design, build, test, and operate software.

• Clear written and verbal communication, including the ability to explain technical trade-offs to non-technical partners.

Play to your strengths. Finding the right fit goes both ways—so this section is yours to complete. When you join, you'll add the unique strengths you bring that aren't captured above.

Our technology environment

We use a mix of product engineering, AI, and platform technologies, including:

AI and application development

• LangChain and LangGraph for orchestration and agent workflows.

• CopilotKit for generative UI patterns.

• AWS Bedrock, OpenAI, Anthropic, and other model providers.

• LangSmith and Langfuse for tracing, telemetry, evaluation, and prompt iteration.

• ClickHouse and PostgreSQL for evaluation datasets, analytics, and AI-related data pipelines.

Platform and infrastructure

• Laravel and PHP across the core product platform, with specialized AI services and pipelines.

• MySQL, Amazon DocumentDB, Typesense, and Redis.

• Containerized, auto-scaling AWS infrastructure defined with Terraform.

• GitHub Actions, Datadog, and BugSnag.

The exact tools will evolve. We value architectural fundamentals, systems thinking, and the ability to choose the right level of complexity over familiarity with a particular framework.