AI Automation Intern (Hybrid, Toronto) at OpenTable

• This role will be required to work from our downtown Toronto office 2 days a week.
  
  

With millions of diners, 60,000+ restaurant partners and 25+ years of experience, OpenTable, part of Booking Holdings, Inc. (NASDAQ: BKNG), is an industry leader with a passion for helping restaurants thrive. Our world-class technology empowers restaurants to focus on what matters most – their team, their guests, and their bottom line – while enabling diners to discover and book the perfect restaurant for every occasion.

Every employee at OpenTable has a tangible impact on what we do and how we do it. You’ll also be part of a global team and its portfolio of metasearch brands. Hospitality is all about taking care of others, and it defines our culture.

This is a hands-on, build-first internship focused on creating AI agents and workflow automations that handle various complex tasks across departments.

You’ll work within a mature AI platform using existing frameworks, tools, and guardrails to build agents that don't just "chat," but execute multi-step tasks like automated triage, document extraction, and data enrichment. Your job is to implement, test, and improve agents and automations under guidance from senior engineers.

This is a production-grade role. You will write code that manages real data, with a focus on reliability, anti-hallucination guardrails, and long-running workflows.

• This is a 12 week internship program.
  
  

In This Role, You Will

• Stateful Agent Orchestration: Build agents using established frameworks like LangChain and LangGraph to manage complex, multi-step workflows with failure recovery and state management.
• Enterprise Integrations: Connect agents to professional toolsets (CRM, Issue Trackers, and Communication platforms) via APIs, OAuth2, and webhooks.
• Advanced RAG & Search: Implement and tune retrieval systems using vector databases (qdrant, pgvector) for high-accuracy similarity search and duplicate detection.
• Computer Vision: Use Vision-based LLMs to extract structured data from unstructured documents.
• Workflow Automation: Implement workflow automations using approved tools (n8n, Zapier, internal platforms).
• Observability: Instrument agents with tools like LangSmith for tracing, performance benchmarking, and cost tracking
  
  

What You’ll Learn (For Real)

• How production AI agents differ from demos
• How to design prompts, tools, and flows that don’t collapse under edge cases
• How to design anti-hallucination guardrails so agents stay on track during long-running tasks
• How to automate business workflows end to end, not just single tasks
• How to write code that meets the rigor of a global engineering organization prioritizing readability and long-term maintenance
• How security, access control, and governance shape AI systems in practice
  
  

What Success Looks Like

• You ship working automations that others rely on
• Your agents fail less over time because you learn how to harden them
• Your code is readable, tested, and easy to extend
• You need less hand-holding by the end of the internship
  
  

Required Skills

• Experience with Python or TypeScript through coursework, projects, or internships
• Basic understanding of LLM concepts (prompting, context windows, tool calling)
• Hands-on use of GenAI tools (OpenAI, Claude, Gemini, etc.)
• Comfort working with APIs, JSON, and webhooks
• Willingness to follow existing frameworks instead of reinventing them
• Familiarity with Retrieval-Augmented Generation (RAG) architectures and how context is retrieved, grounded, and passed to LLMs
  
  

Nice to Have

• Prior exposure to LangChain, LangGraph, AutoGen, or similar frameworks
• Experience with automation tools like n8n or Zapier
• Familiarity with Git, code reviews, and basic testing
• Exposure to vector databases, and managed LLM services
  
  

Why This Is a Strong Learning Opportunity

Most people learn AI through notebooks and demos. This role teaches you how AI behaves when it has to run every day, interact with real systems, and survive messy inputs.

By The End Of 12 Weeks, You’ll Have

• Shipped multiple production automations
• Written real agent code used by teams
• Learned how to debug and harden AI systems
• Built experience that translates directly to full-time AI engineering roles
  
  

There are a variety of factors that go into determining a compensation range, including but not limited to external market benchmark data, geographic location, and years of experience sought/required. The hourly rate for this Toronto, Canada based role is $42 CAD.

Work Environment & Flexibility

At OpenTable, we pride ourselves on fostering a global and dynamic work environment. As a team member with us, you will benefit from a schedule tailored to accommodate a global workforce operating across multiple time zones. While the majority of your responsibilities may align with conventional business hours, there will be instances where you are expected to manage communications - via calls, Slack messages, or emails - outside of regular working hours to effectively collaborate with international colleagues, respond to restaurant partners, and/or address urgent matters. OpenTable will always abide by and consider local laws and regulations.

Inclusion

We’re committed to creating a workplace where everyone feels they belong and can thrive. We know the best ideas come when we bring different voices to the table, so we're building a team as dynamic as the diners and restaurants we serve—and fostering a culture where everyone feels welcome to be themselves.

If you need accommodations during the application or interview process, or on the job, we’re here to support you. Please reach out to your recruiter to request any accommodations.