SeatPick is a profitable, bootstrapped B2C startup

Redefining how fans discover and buy tickets to live events worldwide. Think of us as “the Skyscanner for live events” – the leading ticket comparison platform for sports, music, and live entertainment.

Millions of fans already rely on SeatPick every year, and we are building the next generation of our platform with an AI-first mindset – bringing smarter discovery, personalization, and automation to a complex global marketplace.

We are now looking for an exceptional AI Engineer to join SeatPick as our first dedicated AI hire and lead the foundations of our AI capabilities across the company.

What You’ll Be Doing:

• Design and deploy end-to-end Generative AI services and agentic workflows that solve real-world ticketing and discovery challenges
• Build AI agents capable of performing complex operations, including personalized event discovery, vibe-based search, and automated decision engines
• Own the full lifecycle of AI-powered products, from ideation and prompt design to production rollout, monitoring, and scaling
• Develop internal tooling and platforms that enable R&D teams to experiment with and ship AI features faster
• Bridge the gap between rapid AI prototyping and production-grade systems, ensuring performance, scalability, reliability, and safety under high traffic
• Partner closely with the founders to define SeatPick’s AI strategy, including cost observability, model selection, and optimization
• Mentor engineers on Generative AI best practices, including prompt engineering, RAG architectures, vector search, and safety guardrails

You’re a Fit If You Have:

• 5+ years of experience in software engineering, including at least 3 years building scalable, distributed, cloud-based systems
• 2+ years of hands-on experience building and deploying LLM-based solutions in production (RAG pipelines, prompt engineering, and agent architectures)
• Strong proficiency in TypeScript / Node.js or Python, with solid experience in modern backend and typed development practices
• Hands-on experience with vector databases and familiarity with evaluation frameworks for LLM performance, quality, and reliability
• Strong foundations in system design, algorithms, and software architecture, with a pragmatic approach to speed versus quality in a scaling product
• Experience building data and feedback loops to capture user signals and continuously improve model quality and relevance
• Comfort owning ambiguous, fast-moving initiatives and building products from zero to one in a dynamic startup environment