• Contribute to and lead feature implementations in a collaborative environment, accounting for open-source community participation where appropriate. • Be responsible for product quality, participate in peer code reviews, continuous integration (CI), and secure engineering. • Coordinate with team leads, architects, and other engineers on solution design and architecture. • Participate in Agile development practices and, where appropriate, educate the team on new features through sprint reviews and demos. • Help shape key technical decisions for the platform.

• Design, implement, and ship AI-driven features and systems into production environments • Lead technical decision-making for AI architecture, data modeling, and system integration within your domain • Partner closely with Product, Engineering, and other stakeholders to translate business needs into scalable technical solutions • Identify and address reliability, scalability, performance, and observability challenges in AI systems • Implement and advocate for best practices for applied AI engineering, including agent evaluation, interpretability, data layer design, and monitoring • Mentor and guide other engineers, raising the bar on AI engineering quality and decision-making • Provide input into technical strategy and roadmap discussions related to AI capabilities and platform evolution

• Design, build, deploy, and maintain highly resilient and scalable features across Toast’s enterprise management products • Lead complex projects that improve functionality and reliability for our customers • Partner with a wide array of teams across Toast • Ensure quality by building automated testing for changes • Roll features out to customers, including monitoring for success • Collaborate with UX and PM on the definition and design of features • Mentor and coach other engineers

• Design and build backend services that power verification orchestration, risk evaluation, and automated approval decisions. • Develop and evolve rule engines and decisioning systems to increase automation coverage across products. • Integrate external data providers (e.g., Plaid) into resilient, scalable workflows. • Improve document automation pipelines including classification, extraction, and fraud detection systems. • Build and maintain APIs, Kafka events, and service contracts that enable product teams to consume verification capabilities. • Partner with ML engineers to productionize risk models and ensure decision correctness at scale. • Contribute to platformization efforts to standardize Verifications stages and enable cross-product reuse. • Strengthen compliance, data integrity, and observability across verification systems.