Site Reliability Engineer – AI Applications

Responsibilities

• Operate and improve the reliability, scalability, and performance of the AI platform, including the AI Gateway, MCP servers, and LLM serving
• Define and maintain SLOs, SLIs, and error budgets
• Build strong observability across infrastructure and AI-specific signals like token throughput and model errors
• Improve performance and cost profile of model and API serving
• Design graceful degradation, fallback, and failover strategies
• Maintain deployment practices using GitLab CI/CD and infrastructure as code
• Lead incident response, post-incident reviews, and capacity planning
• Partner with software engineers, data scientists, and ML engineers to productionize AI services

Requirements

• Proven experience in SRE, platform engineering, or backend engineering in distributed environments
• Strong understanding of reliability engineering practices (SLOs, error budgets, observability)
• Strong programming skills in Python and practical experience with Rust
• Hands-on experience with cloud platforms, Docker, and Kubernetes
• Experience building and maintaining CI/CD pipelines, preferably with GitLab
• Solid understanding of distributed systems, microservices, APIs, and networking
• Clear communication and collaboration skills

Preferred Qualifications

• Experience operating AI infrastructure (AI gateways, MCP servers, LLM serving stacks)
• Familiarity with RAG and agentic architectures
• Experience with GPU-backed inference and high-throughput serving
• Experience with serverless, event-driven systems, or streaming platforms
• Familiarity with AI safety, governance, and data privacy

About the Company

Ubisoft is a global leader in gaming with teams across the world creating original and memorable gaming experiences, from Assassin’s Creed, Rainbow Six, to Just Dance and more.