Site Reliability Engineer – AI Applications (M/W/X)
Core
Operate and improve the reliability, scalability, and performance of the AI platform powering Ubisoft's AI applications (hybrid search, Q&A, document generation, assistants).
Role type
Senior Site Reliability Engineer (AI Infrastructure)
Builds
AI Gateway, MCP servers, LLM serving infrastructure, retrieval services, and platform components for production AI applications.
Domain
Gaming industry + AI Infrastructure / Distributed Systems
Deliverable
production ML models
Required skills
Python, Rust, Kubernetes, Docker, Cloud platforms, CI/CD (GitLab), Infrastructure as Code, Distributed systems, SLO/SLI/Error Budgets, Observability, Incident management, Capacity planning, Graceful degradation/failover design.
Preferred skills
AI infrastructure (gateways, MCP, LLM serving), RAG/Agentic architectures, GPU-backed inference, Serverless/Event-driven systems, AI safety/governance.
Technologies
GitLab CI/CD, Kubernetes, Docker, Python, Rust, Cloud platforms, Vector databases, Embeddings.
Responsibilities
Operate and improve reliability/scalability of AI platform; Define and maintain SLOs/SLIs/error budgets; Build observability for AI-specific signals (latency, token throughput, cost); Improve performance/efficiency of model/API serving; Design graceful degradation and failover strategies; Maintain safe deployment practices; Lead incident response and capacity planning; Partner with engineers/data scientists to productionize AI services.
Seniority
Senior, hands-on IC
