Senior AI Platform Developer

Petal is a leading Canadian healthcare orchestration and billing company that revolutionizes healthcare systems to make them agile, efficient, and resilient by enabling the forecasting and shaping of world-class healthcare through Healthcare BI, advanced analytics, and informed insights. 

Our commitment to fostering an exceptional workplace culture has earned us notable recognitions, including being listed as a Great Place to Work in both the technology and healthcare sectors. Join us in our mission to empower healthcare innovators and improve healthcare differently. 

Let’s talk tech

Join a high-performing engineering team undergoing an AI-driven transformation of the Software Development Life Cycle into an Agentic Development Life Cycle (ADLC). We are looking for senior developer who embrace AI-assisted engineering practices and can lead by example in modern software delivery.

You will help drive engineering excellence by leveraging AI tools to improve development velocity, code quality, automation, and operational efficiency across the SDLC.

The role

The AI Platform team builds the dedicated AI capabilities that enable Petal product teams to create, deploy, evaluate, govern, and operate AI agents safely and consistently.

As a Senior Software Developer, AI Platform, you will bring 10+ years of hands-on experience building and operating SaaS products. In this role, you will design, build, and operate production-grade AI Platform capabilities that are reused across product teams. You will help define the technical foundation for Petal’s AI agent ecosystem while ensuring the platform capabilities are secure, observable, evaluable, governed, and ready for production use.

What you’ll do

• Design, build, and operate AI-specific platform capabilities used by product teams to build and run AI agents.

• Build services for agent orchestration, runtime execution, tool integration, agent lifecycle management, evaluation, observability, and governance.

• Create AI Platform components such as agent catalogs, workflow builders, Agent IAM, agent operational stores, evaluation frameworks, prompt/configuration management, guardrails, retrieval services, and Agent Observability.

• Build reusable APIs, SDKs, templates, reference implementations, and documentation for AI agent development and operation.

• Partner with application teams to understand their AI Platform needs while keeping ownership of product-specific AI features with those teams.

• Support secure and governed integration between agents, internal APIs, data sources, knowledge systems, and Azure AI services.

• Define standards for agent deployment, monitoring, evaluation, access control, cost management, and responsible AI practices.

• Reduce duplicated AI-agent infrastructure across teams by creating reusable AI-specific building blocks.

• Mentor developers and help shape technical direction across Petal’s AI Platform capabilities.

Technology stack

You will work with AI Platform technologies such as:

• Azure AI and cloud: Azure Native Services, Azure AI Foundry, Azure AI Search, Azure Cognitive Services

• Agent orchestration: LangGraph, agent runtimes, tool calling, workflow orchestration

• Languages and frameworks: Python, Node.js, TypeScript, Angular

• Evaluation: AI evaluation frameworks, automated agent testing, benchmark suites, quality scoring

• Agent security: Agent IAM, role-based access control, secrets management, audit trails

• Agent observability: Agent traces, tool-call logs, prompt/response monitoring, metrics, dashboards, alerting

• Knowledge and retrieval: Semantic search, vector search, retrieval pipelines, enterprise knowledge connectors

• Governance: Responsible AI guardrails, policy enforcement, compliance controls, cost monitoring

What you bring

• Strong experience building production-grade backend, platform, AI infrastructure, or agent infrastructure services.

• Experience designing distributed systems, APIs, cloud-native services, and developer-facing capabilities for internal engineering teams.

• Hands-on experience with modern AI/LLM infrastructure, such as agent orchestration, retrieval, tool calling, evaluation pipelines, Agent IAM, Agent Observability, model gateways, or responsible AI guardrails.

• Strong understanding of how to build AI systems that are secure, observable, testable, governed, reliable, and cost-aware in production.

• Ability to work through ambiguity, define technical direction, and turn AI Platform concepts into usable services for product engineering teams.

• Strong collaboration skills across product, engineering, security, data, and application teams.

• Ability to mentor other developers and raise the technical bar for AI platform engineering.

Senior-level expectations

As a senior member of the AI Platform team, you will help shape Petal’s AI-specific platform capabilities.

You are expected to:

• Own complex AI Platform initiatives from design through production.

• Make pragmatic architecture decisions that balance speed, safety, scalability, maintainability, governance, and cost.

• Anticipate operational, security, and quality risks specific to AI agents.

• Create reusable AI Platform patterns rather than one-off product features or generic platform services.

• Help application teams succeed through AI-specific enablement, documentation, APIs, and reusable services.

• Mentor developers and influence engineering practices for AI agent development and operation.

• Represent the AI Platform team in cross-functional technical discussions about AI architecture, AI safety, AI evaluation, and agent operations.

Success in the first 6–12 months

Success in this role looks like:

• Application teams can build AI agents faster using dedicated AI Platform capabilities.

• Core AI Platform components are production-ready, observable, secure, governed, and documented.

• There is less duplicated AI-agent infrastructure across teams.

• The platform provides clear AI-specific patterns for orchestration, retrieval, evaluation, governance, Agent IAM, Agent Observability, and deployment.

• AI agents can be evaluated, monitored, governed, and operated with confidence in production.

• The AI Platform team is recognized as the owner of reusable AI Platform capabilities, not as a generic platform team or a product AI feature team.

Petal’s position on remote working

In our opinion, a company cannot claim to be modern, innovative and have the well-being of their team at heart, without attempting to integrate remote working to the level that their business model allows them to. Petal employees continue to benefit from the option of teleworking up to the maximum flexibility permitted by the nature of the position and the smooth running of operations.

Our benefits

• Recurring hybrid work allowance;

• Compensation that recognizes your contribution;

• 4 to 6 weeks of paid vacation per year;

• 5 ​paid personal days​ per year​;

• A ​group RRSP / DPSP plan with employer contribution;

• ​A ​complete group ​insurance ​plan, from day 1;

• An ​annual wellness allowance;

• Access to the Lumino Health™ telehealth application;

• Flexible work hours and more.

Petal is an active participant in the equal opportunity employment program, and members of the following target groups are encouraged to apply: women, people with disabilities, aboriginal peoples and visible minorities. If you are a person with a disability, assistance with the screening and selection process is available on request.

A quick important note: We’ve noticed that some external websites are posting our job openings under incorrect job titles. To find our real opportunities and join our team, please make sure to apply through our official careers page or our trusted partners. We can’t wait to hear from you!