About the Role
Role details below.
Responsibilities
- Build and evolve the systems that enable agents to discover, invoke, and safely execute capabilities across Canva at scale, from initial foundations through to long-term platform maturity.
- Design tool schemas and definition patterns that maximize LLM tool selection accuracy and reliable invocation across diverse agent consumers and AI integrations.
- Build and operate evaluation pipelines that measure tool calling behavior in production, catch regressions, and drive continuous quality improvement.
- Collaborate with product, platform, and GenAI teams to integrate agentic capabilities into production systems and understand how tool use behaves at real-world scale.
- Advise contributing teams on how to define tools agents can reliably call, lowering the bar for onboarding new capabilities into the shared agentic layer.
- Partner with platform engineers on governance, safety, and execution guarantees, so the platform earns trust as a company-wide dependency for AI integrations.
- Stay close to developments in agentic AI (MCP, function calling, A2A protocols) and apply new approaches where they meaningfully improve tool interoperability.
- Mentor engineers on agentic integration patterns and evaluation methodology.
Requirements
- Hands-on production experience with LLM tool-use and function calling
- Experience designing tool schemas
- Understanding of how model behavior is shaped by tool definitions
- Experience shipping agentic integrations to real users
- Built evaluation frameworks that measure AI feature quality systematically
- Use evaluation signals to drive improvement rather than just report them
- Java proficiency is essential
Nice to Have
- Python or TypeScript proficiency is a strong plus
- Experience at the boundary of ML and platform engineering
- Collaboration with backend or infrastructure teams to make AI integrations production-grade, safe, and scalable
- Familiarity with MCP, LangChain, LangGraph, or agent frameworks
- Prompt engineering experience specifically for tool definitions and tool calling schemas
Work Arrangement
Remote (Country)
Team
Structure: Part of the Ecosystem Supergroup; works closely with GenAI teams, product, and platform engineering.
Additional Information
- This role is not a fit for candidates with research-only backgrounds
- This role is not suitable for candidates with traditional ML without LLM/GenAI exposure
- This role is not suitable for candidates with data engineering experience presented as ML engineering
- The candidate will work at the frontier of agentic AI on making tool calling reliable and measurable at production scale
- The candidate will build deep expertise in AI integration architecture
- The candidate will develop cross-functional influence by working across GenAI, Ecosystem Platform, and product teams
- The candidate will gain broad exposure to the evolving agentic ecosystem: MCP, function calling protocols, A2A communication, and how frontier models are changing tool use patterns
- The candidate will grow into a role with real technical scope, where evaluation systems and tool calling standards shape how Canva's agents behave for millions of users
