27 days ago
Saint-Mandé, FranceMid Level
Responsibilities
- Operate and improve the reliability, scalability, performance, and cost efficiency of the AI platform, including the AI Gateway, MCP servers, LLM serving, retrieval services, and related platform components.
- Define and maintain SLOs, SLIs, and error budgets to guide reliability decisions.
- Build observability for infrastructure, services, and AI-specific signals such as latency, token throughput, model and provider errors, cost, saturation, and quality indicators.
- Design graceful degradation, fallback, and failover strategies across models, providers, and regions.
- Maintain safe deployment practices using GitLab CI/CD, infrastructure as code, automated testing, and progressive delivery.
- Participate in incident response, post-incident reviews, capacity planning, runbook development, and reliability improvements.
- Collaborate with software engineers, data scientists, ML engineers, security teams, and product stakeholders to productionize AI services.
Requirements
- Proven experience in SRE, platform engineering, backend engineering, or infrastructure roles in compute-intensive, data-intensive, or distributed environments.
- Strong knowledge of reliability engineering, including SLOs, error budgets, observability, capacity planning, incident management, and post-incident analysis.
- Strong Python programming skills and practical Rust experience, or willingness to work deeply with Rust-based services.
- Hands-on experience with cloud platforms, Docker, Kubernetes, production-grade service operations, CI/CD pipelines, and infrastructure as code.
- Understanding of distributed systems, microservices, APIs, networking fundamentals, and production debugging.
- Ability to collaborate across engineering, data, ML, security, and product teams.
- Preferred experience includes AI gateways, MCP servers, LLM serving stacks, model routers, provider abstraction layers, RAG, agentic architectures, embeddings, vector databases, hybrid search, GPU-backed inference, high-throughput serving, serverless systems, event-driven systems, queues, streaming platforms, AI safety, governance, auditability, or data privacy.
Benefits
- Permanent contract.
- Office-based work at Ubisoft’s Saint-Mandé office; the building includes a gym.
- Profit sharing, a yearly company savings plan, 25 paid time-off days, and 12 additional paid days off.
- 50% of the transportation pass, lunch vouchers of 9€/day, healthcare for the employee and family, and additional Ubisoft perks.
- 20 weeks of maternity leave and 7 weeks of paternity/co-parental leave.
Tech Stack
Categories
DevOpsSite Reliability
About Ubisoft
Ubisoft develops and publishes video games for console, PC, and mobile players worldwide, monetized through premium titles, downloadable content, live services, and the Ubisoft+ subscription. Founded in 1986 and headquartered in Saint-Mandé, France, it operates studios globally and is publicly traded on Euronext Paris. Franchises include Assassin’s Creed, Far Cry, Tom Clancy’s Rainbow Six, and Just Dance.