Senior AIOps Engineer

As a Senior AIOps Engineer, you won't just be managing servers; you will be the architect of the "Golden Paths"-the reusable, automated infrastructure that enables our product teams to ship LLMs, Vector Search, and AI Agents faster than ever before., * Architect the AI Stack: Design and operate core infrastructure on Kubernetes, including Vector Databases, LLM Gateways (LiteLLM), and workflow automation tools (n8n).

• Enable at Scale: Drive AI adoption by creating self-service "Golden Paths" using Terraform and Helm, allowing engineering teams to deploy RAG pipelines with one click.
• Operational Excellence: Implement centralized observability, tracing (Langfuse), and governance to ensure our AI systems are reliable, auditable, and secure.
• Fiscal Discipline: Own the "AI Bill"-monitoring token usage and latency to optimize spend while maintaining high performance., You will work with a cutting-edge stack including Kubernetes, LiteLLM, Open WebUI, n8n, Langfuse, and Vector Databases, all running within a modern cloud-native ecosystem.

• Platform Expertise: 5+ years in Platform Engineering, SRE, or DevOps within a cloud-native environment.
• Kubernetes Mastery: Deep experience managing stateful and stateless workloads (Helm, Istio, Docker).
• AI Infrastructure Fluency: Hands-on experience deploying and operating AI/ML tools or data-intensive systems in production.
• Coding Proficiency: Strong skills in Python or Go to build custom API wrappers and automate operational tasks.
• Monitoring & Tracing: Expertise in Prometheus, Grafana, and ELK stack to ensure end-to-end observability of complex AI requests.

Groupon is a marketplace where customers discover new experiences and services everyday and local businesses thrive. To date we have worked with over a million merchant partners worldwide, connecting over 16 million customers with deals across various categories. In a world often dominated by e-commerce giants, we stand out as one of the few platforms uniquely committed to helping local businesses succeed on a performance basis. Groupon is on a radical journey to transform our business with relentless pursuit of results. Even with thousands of employees spread across multiple continents, we still maintain a culture that inspires innovation, rewards risk-taking and celebrates success. The impact here can be immediate due to our scale and the speed of our transformation. We're a "best of both worlds" kind of company. We're big enough to have the resources and scale, but small enough that a single person has a surprising amount of autonomy and can make a meaningful impact.