Now, more than ever, the Toast team is committed to our customers. We’re taking steps to help restaurants navigate an increasingly complex world with intelligent, AI-powered experiences. Our mission is to build a restaurant platform that helps operators adapt, take control, and focus on what they love most—running their businesses. By investing in cutting-edge AI systems that are purpose-built for restaurants, we’re shaping the future of how restaurants operate, decide, and grow.

Bready* to make a change?

As an AI Engineer focused on Agentic Workflows, you will design and build intelligent, autonomous systems that orchestrate reasoning, actions, and tools to solve complex business problems. You will work at the intersection of LLMs, systems engineering, and product innovation—partnering with Data Science, ML Engineering, Product, and Platform teams to bring agent-based capabilities into production across Toast.

You will help define how AI agents plan, reason, collaborate, and execute tasks at scale—powering next-generation experiences across fraud, forecasting, operations, and customer insights.

About this Roll*:

• Design and build agentic AI workflows using LLMs to autonomously reason, plan, and act across complex tasks
  
  
• Architect multi-agent and tool-using systems that integrate with internal services, APIs, and data platforms
  
  
• Collaborate closely with Product, Data Science, ML Engineering, and Platform teams to translate business problems into agent-driven solutions
  
  
• Break down large AI initiatives into iterative, shippable components that deliver incremental value
  
  
• Productionize agent workflows with strong observability, reliability, and performance guarantees
  
  
• Implement evaluation, monitoring, and guardrails for agent behavior, correctness, latency, and cost
  
  
• Incorporate human-in-the-loop patterns where appropriate to ensure safety, trust, and usability
  
  
• Document architectures, decisions, and best practices to enable team-wide adoption and scalability
  
  
• Stay current with advancements in LLMs, agent frameworks, prompting strategies, and AI safety
  
  
• Contribute to building a strong AI engineering culture within the Data & AI organization

 

Do you have the right ingredients*?

• Bachelor’s or Master’s degree in Computer Science, AI, ML, or related technical field
• 5+ years of experience in full stack Data Scientist, ML engineering, or applied AI roles
• Hands-on experience with LLMs and agentic systems (e.g., LangChain, LangGraph, AutoGen, custom frameworks)
• Strong proficiency in Python and experience building production-grade systems
• Experience integrating LLMs with tools, APIs, databases, and workflows
• Experience deploying LLM-based systems at scale
• Solid understanding of software engineering best practices: OOP, testing, CI/CD, version control
• Experience in building and productionising embedding models, Data classical ML and deep learning models. 
• Familiarity with cloud-native systems and AWS services (ECS, EKS, Lambda, DynamoDB, S3, SageMaker, etc.)
• Ability to reason about trade-offs in latency, cost, reliability, and correctness
• Strong collaboration and communication skills across technical and non-technical stakeholders
  
  

Bonus ingredients*:

• Familiarity with AI evaluation frameworks, prompt optimization, and model observability
• Knowledge of AI safety, governance, and responsible AI practices
• Passion for experimentation, innovation, and shaping the future of applied AI