Context:

Infomaniak is developing an open source AI platform hosted on its own Swiss data centres. We deploy large-scale language models and build intelligent agents for our products (kChat, kMeet, kDrive). We are looking for an AI Engineer to design, implement and optimise our AI agents, focusing on quality, reliability and user experience.

Your responsibilities :

• Deployment & Orchestration: Deploy, maintain and optimise LLMs on Kubernetes by maximising GPU / Compute resource efficiency.
• CI/CD & Automation Improve and industrialise our Gitlab CI pipelines for AI models (build, test, deployment, rollback). Manage deployments via Flux CD (GitOps).
• Monitoring & Observability: Strengthen our Prometheus / Grafana / Victoria Metrics stack for detailed visibility on performance, GPU consumption, latency, availability and overall health of AI services.
• Resource optimisation : Work on cost and performance efficiency (autoscaling, scheduling, quota management, image optimisation...)
• Quality & Reliability: Ensure robustness, security and reproducibility of deployments in a critical environment

The profile that excites us:

• Mastery of modern serving frameworks (e.g. vLLM, TGI, TensorRT-LLM...)
• Mastery of GitLab CI (pipelines, runners, variables, integration with Kubernetes).
• Proven experience with Kubernetes (operators, Helm, CRDs, networking, autoscaling).
• Experience with Flux CD (GitOps, HelmReleases, Kustomize, deployment automation).
• Experience with Prometheus / Grafana (dashboards, alerting, exporters).
• Knowledge of GPU infrastructures (NVIDIA, CUDA, GPU scheduling, monitoring).
• Passion for quality, reliability and performance.
• Ability to work in a critical environment (high SLA, high availability).
• Good ability to collaborate with ML and Dev teams.

A plus if you have knowledge in:

• Technical curiosity, taste for innovative challenges and optimisation.
• Open source contributions or side projects are appreciated
• You enjoy working in a team and demonstrate positive communication
• Your humour, flexibility and team spirit are essential assets for working in a fun environment

The technical stack we use

• LangChain
• Pydantic-ai
• vLLM
• FastAPI
• Gitlab
• Sentry
• Qdrant

The position:

• Permanent contract
• Work rate: 80 - 100%
• Location: Geneva
• Availability: As soon as possible

Recruitment process steps:

• A first technical interview to validate your skills.
• A second interview at our offices

Why Infomaniak:

• Be part of a company shaping an ethical cloud that respects privacy, people and the environment.
• Work every day in a caring, balanced environment with your personal life and extremely stimulating with people at the forefront of their field who are committed, attentive and passionate about what they do.
• Make a real difference in the lives of millions of users worldwide. At Infomaniak, we are all united by the feeling of having real responsibilities and contributing to something bigger.
• Meet diverse people in a friendly atmosphere during very regular company outings (Afterwork, skiing, cycling, theatre, etc.).
• Work in a very pleasant atmosphere and an original workspace, where meeting rooms are carefully decorated and foster inspiration as well as collaboration.
• Enjoy many other benefits such as an annual bonus encouraging soft mobility, a fitness room to keep fit, availability of electric bikes and scooters, convivial relaxation areas (rest room, video and arcade games, pinball, table football, etc.), excellent accident and loss of earnings coverage, and more surprises.

At Infomaniak, we are committed to diversity, equity and inclusion of employees in the workplace. Our job offers are open to all and all applications are evaluated on an equal footing, regardless of gender, origin, religion, sexual orientation or disability of the candidates.