Digital Agent Developer
- Location
- Mississauga, Canada
- Employment
- Full Time
- Work model
- On-Site
- Level
- Mid
- H-1B history
- 49 approvals (FY2023)
- Posted
Skills
About this role
McKesson is an impact-driven, Fortune 10 company that touches virtually every aspect of healthcare. We are known for delivering insights, products, and services that make quality care more accessible and affordable. Here, we focus on the health, happiness, and well-being of you and those we serve – we care. What you do at McKesson matters. We foster a culture where you can grow, make an impact, and are empowered to bring new ideas. Together, we thrive as we shape the future of health for patients, our communities, and our people. If you want to be part of tomorrow’s health today, we want to hear from you. McKesson is transforming healthcare experiences through AI-powered digital agents. As a Digital Agent Developer, you will design, build, test, and continuously improve conversational AI solutions that support customers and business teams across voice, chat, and email channels. You will work within the Sierra Agent OS ecosystem to create reusable agent patterns, optimize customer interactions, and improve AI performance through testing, analytics, and iterative tuning. This role partners closely with platform engineers, solution architects, and business stakeholders to deliver scalable, secure, and effective AI-powered experiences. This role sits on McKesson's Contact Center AI team, which is using AI and digital agent capabilities to transform and improve the end-to-end customer journey across voice, chat, and email for McKesson's businesses. The team designs, builds, and runs digital agents on Sierra Agent OS and connects them to the contact center and enterprise systems around them. This is the role where new agents and new capabilities get built and existing ones get better. Sierra is a new platform, so hands-on Sierra experience is a plus, not a requirement; we will ramp you on it. What we do need is real experience building AI agents: prompts, tool calling, handoffs, testing, and the judgment to know when an agent is wrong. WHAT YOU’LL DO Design, configure, and optimize conversational AI agents within Sierra Agent OS. Build reusable reference models and design patterns for multiple business use cases. Develop and refine agent experiences across voice, chat, and email channels. Analyze conversation data and performance metrics to improve accuracy, containment, and customer outcomes. Create and optimize prompts, workflows, decision logic, and handoff experiences. Collaborate with platform engineers and solution architects on multi-LLM orchestration strategies. Support testing, deployment, monitoring, and continuous improvement of AI agent solutions. Run agent simulations and regression tests before each release, and review production conversations where the agent fell short to find the cause and fix it. Work with the integration and platform teams on the APIs and tools the agents call (account lookup, order status, case creation, appointment scheduling) and on how the agent should behave when those calls fail. Maintain agent documentation, test cases, and the support runbooks that the service desk and L3 support teams rely on. Follow enterprise security, compliance, documentation, and governance standards.
BASIC REQUIREMENTS
2+ years of experience building AI agents or conversational AI solutions (LLM-based assistants, chatbots, voicebots), or in AI/ML or software development with hands-on agent work. Bachelor's degree in Computer Science, Engineering, Information Technology, Data Science, or equivalent experience. Hands-on experience designing, building, or tuning LLM-based AI agents or digital assistants, including prompts, tool and function calling, workflows, guardrails, and handoff to a human agent. Hands-on experience with prompt engineering, conversational design, intent modeling, or Natural Language Understanding (NLU). Working knowledge of agentic AI patterns: multi-step tool use, retrieval (RAG), evaluation and testing of agents, and the ways an agent can fail in production. This can come from