Senior AI Platform Lead - Kubernetes & LLM Ops

ICRC

Genf

Hybrid

CHF 150,000 - 210,000

Full time

9 days ago

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

The International Committee of the Red Cross (ICRC) seeks an AI Platform Lead to own and evolve a hybrid AI platform that powers centralized AI services across the organization. You will guide platform vision, roadmaps and backlog, enable secure model deployment on GPU hardware and ensure scalable, compliant, and reusable AI services for product teams and data scientists.

You will collaborate with security, network and Kubernetes teams, design self-service ML workflows, and mentor engineers to

Qualifications

Bachelor’s or Master’s degree in Computer Science, Engineering, Data Science or a related field, or equivalent professional experience.
10+ years of experience in software, DevOps or platform engineering, including 4+ years deploying and operating applications on Kubernetes-based platforms in production, and demonstrated experience with AI/ML or GPU workloads.
Proven track record of deploying and operating production-grade AI or data services on Kubernetes (e.g. Helm, operators, resource quotas, ingress, persistent storage) in collaboration with a Kubernetes platform team.
Hands-on experience deploying and serving ML and LLM models on GPU infrastructure, including GPU operators and drivers, GPU sharing and scheduling, inference engines and performance tuning.
Experience designing and operating an AI/LLM gateway (e.g. LiteLLM), including model delivery, MCP, consumption monitoring and guardrails, working with security and network teams on perimeter and access controls.
Experience in infrastructure as code, GitOps and CI/CD tooling (e.g. Terraform, Ansible, Helm, Argo CD, GitLab CI) and in integration with observability stacks (e.g. Prometheus, Grafana, OpenTelemetry).
Proven experience managing a technical backlog and roadmap in an Agile delivery environment, translating user needs into platform capabilities.
Certification or experience in Agile delivery. SAFe certification is an asset.
Experience with self‑service ML platforms (e.g. OpenShift AI, Kubeflow, MLflow) is a strong asset.
Kubernetes certification (e.g. CKA, CKAD) is an asset.
Experience in a complex, diverse international environment is an asset.
Excellent written and spoken English. French is an asset.
Proficiency in Python and scripting languages.
Good understanding of MLOps practices, including model versioning, registry, monitoring and lifecycle management.
Good knowledge of AI concepts such as agentic AI and MCP, and of the services they require (e.g. vector databases). Knowledge of graph databases is an asset.
Proven API design and integration skills across heterogeneous systems and partners.
Knowledge of data privacy regulations, information security and ethical considerations in AI.
Strong stakeholder management and communication skills, with the ability to engage technical and non-technical audiences, including senior leaders, and to manage suppliers.

Responsibilities

Own the AI platform vision, roadmap and backlog. Prioritize features, improvements and technical debt with product owners, AI teams and other stakeholders, balancing user needs, security, cost and capacity.
Manage the deployment and operation of centralized, transversal AI services on the hybrid Kubernetes platform, making them reusable across ICRC products.
Work closely with the Kubernetes product team on workload requirements, namespaces, resource quotas and release practices.
Manage model deployment on GPU infrastructure. Serve open-source and third-party models with appropriate inference engines, covering GPU scheduling and sharing, capacity planning, autoscaling, performance tuning and model release and rollback.
Co-design and operate the AI gateway with security and network teams responsible for perimeter security and access controls. Run it as a single governed access point for model delivery, MCP servers, consumption monitoring and guardrails.
Design and operate self-service capabilities that enable advanced users to develop, train and deploy models in a governed environment, including workbenches, pipelines, model registry and resource quotas.
Provide shared AI building blocks, such as vector and graph databases, agent components, MCP servers, model registry and experiment tracking, as documented services.