17 days ago
Saint-Mandé, FranceSenior
Responsibilities
- Operate and improve the reliability, scalability, and performance of the AI platform, including AI Gateway, MCP servers, LLM serving, retrieval services, and related components.
- Define and maintain SLOs, SLIs, and error budgets to guide reliability and platform stability decisions.
- Build observability for infrastructure, services, and AI-specific signals including latency, token throughput, provider errors, cost, saturation, and quality indicators.
- Improve model and API serving performance, efficiency, and cost across cloud, containerized, and high-throughput environments.
- Design graceful degradation, fallback, and failover strategies across models, providers, and regions.
- Maintain deployment practices using GitLab CI/CD, infrastructure as code, automated testing, and progressive delivery.
- Lead or contribute to incident response, post-incident reviews, capacity planning, and reliability improvements.
- Partner with software engineers, data scientists, ML engineers, security teams, and product stakeholders to productionize AI services.
- Establish operational standards, runbooks, dashboards, and best practices for AI application reliability.
Requirements
- Proven experience in SRE, platform engineering, backend engineering, or infrastructure roles in compute-intensive, data-intensive, or distributed environments.
- Strong understanding of SLOs, error budgets, observability, capacity planning, incident management, and post-incident analysis.
- Strong programming skills in Python and practical experience with Rust, or willingness to work deeply with Rust-based services.
- Hands-on experience with cloud platforms, Docker, Kubernetes, and production-grade service operations.
- Experience building and maintaining CI/CD pipelines, preferably with GitLab, and working with infrastructure as code.
- Understanding of distributed systems, microservices, APIs, networking fundamentals, and production debugging.
- Ability to work in a fast-changing AI ecosystem while applying SRE rigor and risk awareness.
- Clear communication and cross-functional collaboration skills.
- Nice-to-have experience with AI gateways, MCP servers, LLM serving stacks, model routers, or provider abstraction layers.
- Familiarity with RAG, agentic architectures, embeddings, vector databases, hybrid search, query processing, tool use, or agent orchestration.
- Experience with GPU-backed inference, high-throughput serving, batching, caching, autoscaling, or model performance optimization.
- Experience with serverless, event-driven systems, queues, streaming platforms, or asynchronous processing.
- Familiarity with AI safety, governance, auditability, data privacy, or secure-by-design platform practices.
- Open-source contributions, technical writing, talks, or publications in relevant engineering, reliability, or AI infrastructure fields.
Benefits
- Permanent contract.
- Office-based work in Saint-Mandé, with stated work flexibility limited to office-based attendance.
- Profit sharing and a yearly company savings plan.
- 25 paid time-off days plus 12 additional paid days off.
- 50% of the transportation pass paid by the company.
- Lunch vouchers valued at 9€ per day.
- Healthcare coverage for the employee and family.
- 20 weeks of maternity leave and 7 weeks of paternity/co-parental leave.
- Additional Ubisoft perks and access to an on-site gym.
Tech Stack
Categories
Site 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.