The company is a global gaming business with teams around the world, and it is rebuilding how its teams work with information using AI. Its teams build and run applications for document-heavy, interactive and intelligent uses such as hybrid search, question answering, document drafting, chat assistants, agent-based workflows and coding helpers.
The team you would join keeps the AI platform reliable, scalable and well run. That covers the AI gateway, MCP servers, LLM serving, retrieval services and the wider platform pieces that let other teams ship AI applications safely.
The work mixes quick-moving AI engineering with careful site reliability practice. You will help the platform change at speed while keeping it observable, resilient, cost-effective and dependable at scale.
You will work on projects that influence how AI platforms are run at scale. You will keep up with new AI infrastructure and reliability practices and help teams deliver useful, safe and dependable AI-powered applications.
The office is in Saint Mandé, a short walk from metro line 1 at Saint Mandé station, and the building has a gym.
Responsibilities
Run and improve the reliability, scalability and performance of the AI platform, including the gateway, MCP servers, LLM serving, retrieval services and related components.
Set and maintain SLOs, SLIs and error budgets, and use them to decide how to trade delivery speed against platform stability.
Build observability across infrastructure, services and AI-specific signals, including latency, token throughput, model and provider errors, cost, saturation and output quality.
Improve the performance, efficiency and cost of model and API serving across cloud, container and high-throughput environments.
Design graceful degradation, fallback and failover, including resilience against model, provider and regional failures.
Keep deployments safe and repeatable using GitLab CI/CD, infrastructure as code, automated tests and progressive delivery where it fits.
Lead or take part in incident response, post-incident reviews, capacity planning and reliability work.
Work closely with software engineers, data scientists, ML engineers, security teams and product stakeholders to take AI services into production responsibly.
Help set operational standards, runbooks, dashboards and reliability practices for AI applications.
Requirements
Proven experience in SRE, platform, backend or infrastructure roles in compute-heavy, data-heavy or distributed systems.
Strong grasp of reliability practice, including SLOs, error budgets, observability, capacity planning, incident management and post-incident analysis.
Strong Python skills, plus practical Rust experience or a clear willingness to work deeply in Rust-based services.
Hands-on work with cloud platforms, Docker, Kubernetes and running production services.
Experience building and maintaining CI/CD pipelines, ideally on GitLab, and working with infrastructure as code.
Solid knowledge of distributed systems, microservices, APIs, networking and debugging in production.
Ability to move fast in a changing AI ecosystem while keeping the rigour and risk awareness an SRE needs.
Clear communication and the ability to work across engineering, data, ML, security and product teams.
Nice-to-have: experience running AI infrastructure such as AI gateways, MCP servers, LLM serving stacks, model routers or provider abstraction layers.
Nice-to-have: familiarity with RAG and agent architectures, including embeddings, vector databases, hybrid search, query handling, tool use and agent orchestration.
Nice-to-have: experience with GPU-backed inference, high-throughput serving, batching, caching, autoscaling or model performance tuning.
Nice-to-have: experience with serverless, event-driven systems, queues, streaming platforms or asynchronous processing.
Nice-to-have: familiarity with AI safety, governance, auditability, data privacy or secure-by-design platform practice.
Nice-to-have: open-source work, technical writing, talks or publications in reliability, engineering or AI infrastructure.
Conditions
The company offers equal opportunities regardless of gender, ethnicity, religion, sexual orientation, social status, disability or age.
Benefits
Profit sharing and a yearly company savings plan.
25 days of paid time off plus 12 additional paid days off.
The company pays 50% of your public transport pass.
Lunch vouchers worth 9€ per day.
Healthcare coverage for you and your family.
Maternity leave of 20 weeks and paternity or co-parental leave of 7 weeks.