• Design, develop, and optimize applications leveraging internal LLM platforms • Create, test, and maintain high-quality prompts to drive accurate and predictable outputs • Apply advanced prompting techniques including: Few-shot prompting, Prompt chaining, RAG (Retrieval-Augmented Generation) • Build full-stack, end-to-end GenAI applications • Design and implement backend services integrating LLMs with enterprise systems • Develop or collaborate on web-based user interfaces • Integrate GenAI capabilities into existing applications and workflows • Analyze structured and unstructured data for GenAI use cases • Translate business requirements into LLM-driven workflows • Document design decisions, prompts, and system behavior clearly

• Defining and leading the creative strategy for Canva's photography and video content - ensuring we're building a library that's diverse, on-trend, and genuinely useful for our users • Driving AI-first approaches to content production: using AI to generate, enrich, tag, and scale photo and video assets that would take years to produce by hand • Partnering with Content Studio's production teams, engineers, and product managers to build tooling and workflows that unlock content creation at scale • Setting quality standards and creative direction across photography and video - commissioning shoots, reviewing assets, and ensuring every piece meets the Canva bar • Contributing to Canva's AI Template Marketplace goals, where photo and video content is a critical ingredient in making templates come alive • Coaching and leading a team of photographers, videographers, and content producers to do the best work of their careers

• Architect and build scalable multi-agent systems • Own backend services, APIs, and data pipelines • Collaborate with Product, Design, and Client teams • Continuously improve existing architecture and reduce operational complexity

• Architect and ship production AI systems end-to-end (orchestration, retrieval, inference, evaluation, and monitoring) for clinical decision support, document understanding, and agentic medical companions. • Design agentic workflows with custom skills and harnesses, using frontier LLMs and self-hosted models where appropriate, and resisting the urge to reach for an agent when a function call would do. • Lead development of structured information extraction pipelines from clinical documents, including automated verification systems and human-in-the-loop gates, where necessary. • Build robust evaluation infrastructure (golden datasets, LLM-as-judge, regression tests, online A/B evaluation) that gates every model and prompt change. Accuracy, safety, cost, and latency are first-class metrics. • Engineer for latency and cost: streaming, caching, prompt compression, model routing, and inference-cost budgets. • Own production health: trace- and span-level observability, prompt versioning, drift detection, cost monitoring, replay-from-production for debugging, PHI-safe logging throughout, and the general art of finding out something is broken before a clinician does. • Operationalize models trained by the AI Scientist team: serving, evaluation in production, rollback paths, and the feedback loops that turn real usage into training and eval data, rather than into a Slack thread nobody reads. • Partner with clinicians, the data engineering team, and our research collaborators to translate clinical requirements into specifications and deliverable systems. • Educate and mentor PMs and engineers across Atria on applied AI best practices, from prompt and evaluation design to choosing the right model for the job (which, surprisingly often, is not the largest one). • Set technical direction for AI engineering at Atria: architecture decisions, build-vs-buy calls, and the evaluation and observability standards the team actually works to. • Raise the bar on engineering practices, code review, observability, and incident response. Quietly, persistently, and with grace. • Drive vendor and partner technical due diligence for AI/ML vendors: BAA scope, PHI handling, sub-processor obligations, and IP terms. • Mentor other AI engineers through code review, design docs, and architecture decisions, with the patient conviction that good systems are made twice: once badly, then properly.