Senior AI Engineer

ROLLER is not your average software-as-a-service company. With a global presence in over 30 countries, we're here to bring some excitement to the leisure and attractions industry and make a difference! Our mission is to help businesses operate smoothly and create fun and memorable guest experiences by providing seamless ticketing, point-of-sale, self-serve kiosks, memberships and digital waiver processes.

But here's the best part: our team. We're a group of 200+ highly passionate, enthusiastic, and down-to-earth professionals located all around the world who are all working together to build something truly remarkable. We're aiming high and believe that the possibilities are endless. As we continue to grow globally, we're excited to write our success story and have fun along the way.

We genuinely love what we do, and we're looking for like-minded people to join us on this amazing journey. If you're ready to be part of a dynamic team and make a real impact, come aboard, and let's create some unforgettable experiences together at ROLLER!

As a Senior AI Engineer, you’ll play a key role in designing and delivering intelligent, scalable systems that harness the power of large language models. You’ll contribute to the development of backend infrastructure and AI-powered features that enhance how venues manage operations and deliver exceptional guest experiences. From optimizing support workflows to enabling smarter data insights and automation, your work will help bring innovative, AI-driven capabilities into the ROLLER platform. Collaborating with cross-functional teams, you’ll help shape the future of guest engagement and operational efficiency for leisure and attractions businesses around the world.

• →Design and develop scalable AI-driven applications and backend systems using Python and modern software engineering practices.
• →Build and deploy AI agents and workflows with frameworks like LangGraph and LangChain, integrating with LLM APIs and toolchains.
• →Implement and maintain retrieval-augmented generation (RAG) pipelines, including embedding strategies and vector database integration.
• →Deploy and manage AI services on Google Cloud Platform (GCP) using tools like Cloud Functions, Vertex AI, and BigQuery.
• →Collaborate cross-functionally to deliver reliable, high-performing AI features with strong observability, testing, and CI/CD.

• Strong proficiency in Python, with a solid understanding of software engineering principles.
• Hands-on experience building AI agents or LLM-powered workflows (LangChain/LangGraph or similar).
• Familiarity with GCP, including deployment, serverless functions, and infrastructure-as-code.
• Experience with RAG architectures, including chunking strategies, embeddings, and semantic search.
• Deep understanding of vector databases and their use in LLM applications.
• Working knowledge of LLM APIs (e.g., OpenAI, Claude, Gemini).
• Understanding of prompt engineering and evaluation methods for LLMs.
• Experience with modern version control, testing, and DevOps workflows.

• Experience with frontend integration of AI systems.
• Familiarity with other cloud platforms (AWS, Azure).
• Knowledge of agentic frameworks beyond LangChain (e.g., Autogen, CrewAI, AgentOps).
• Background in data pipelines, orchestration tools (e.g., Airflow), or real-time data processing.
• Open source contributions or AI-focused technical writing.