Geforderte Skills
- AI Ops
- AI Agents
- Coding Agents
- LLM Services
- Kubernetes
- Platform Engineering
- Infrastructure as Code
- Automation
- CI/CD
- Observability
- FinOps
- Security
Sprachen: French
Jobbeschreibung
Experienced Platform Engineer needed to coach teams on AI/agent usage in Ops, build and automate an 'agent-ready' platform, and manage Kubernetes infrastructure. Requires 8+ years of experience with AI Ops, LLM deployment, and Kubernetes.
Project overview
Context
Experienced professional, with a minimum of 8 years of experience, responsible for coaching and training production and infrastructure teams to operate an 'agent-ready' platform and to use AI and agents in their Ops work. The role involves building infrastructure and platform as code, automating their delivery, and transforming them into secure, resilient, and cost-controlled self-service services.
Missions
Tools and environment
Working conditions
Criteria
- Use coding agents (e.g., Claude Code, Codex, OpenCode, Cursor) and AI for Ops tasks: troubleshooting, scripting, runbooks, and infrastructure changes.
- Deploy and operate LLM services and agent workloads, including LLM gateways, MCP servers, and sandbox actions.
- Monitor, tool, and evaluate agents in production, tracking their behavior, quality, and token costs.
- Coach and train production and infrastructure engineers on the platform and on the use of coding agents and AI for Ops and automation.
- Build and operate the 'agent-ready' platform, ensure its security and resilience, and then open it up to new teams.
- Handle incidents, access requests, and changes on the platform.
- Define, with development and security teams, the access model, pre-approved changes, and audit trail.
- Package the platform configuration for reusability by other teams, and report on its usage and costs.
- Design the Kubernetes platform: build and operate clusters, namespaces, RBAC, quotas, storage (S3, persistent volumes, local SSD), and container registry.
- Manage workload isolation for agents and ephemeral test environments, including rapid database cloning (e.g., with Ceph).
- Manage secrets and access (HashiCorp Vault, least privilege service accounts), network flows, and proxies.
- Infrastructure as code: Terraform, Helm, Ansible
- GitOps: Argo CD
- Pipelines as code: Jenkins, GitLab CI, webhooks, runners
- Automation scripts: Python, Go
- Infrastructure observability: Splunk, Grafana, OpenTelemetry
- Other languages and frameworks: Java, Angular, .NET, C, SQL
- Agent security: identity and access control for AI workloads
- FinOps and capacity planning for AI workloads
- Enterprise Kubernetes distributions (OpenShift or equivalent)
- Kubernetes certifications (CKA, CKS) or coaching and upskilling experience
- Work with SRE and DevOps teams
- Experience in a regulated asset management or banking environment
- Minimum 8 years of experience
- Ability to coach and train production and infrastructure teams on the use of AI and agents in Ops
- Experience in building infrastructure and platform as code, delivery automation, and creating secure, resilient, and cost-controlled self-service services
- Experience with AI-augmented Ops and coding agents (e.g., Claude Code, Codex, OpenCode, Cursor) for troubleshooting, scripting, runbooks, and infrastructure changes
- Experience deploying and operating LLM services and agent workloads (e.g., LLM gateways, MCP servers, sandbox actions)
- Skills in monitoring, tooling, and evaluating agents in production: behavior, quality, and token costs
- Experience in Kubernetes platform engineering: building and operating clusters, namespaces, RBAC, quotas, storage (S3, persistent volumes, local SSD), and container registry
- Knowledge of workload isolation for agents and ephemeral test environments, including rapid database cloning (e.g., Ceph)
- Experience managing secrets and access (HashiCorp Vault, least privilege service accounts), network flows, and proxies
- Valued skills in CI/CD, automation, and observability: Infrastructure as Code (Terraform, Helm, Ansible), GitOps (Argo CD), pipelines as code (Jenkins, GitLab CI), and automation scripts (Python, Go)
- Experience with infrastructure observability tools (Splunk, Grafana, OpenTelemetry), incident and change management
- Knowledge of other languages and frameworks such as Java, Angular, .NET, C, or SQL
- Understanding of agent security, including identity and access control for AI workloads
- Experience with FinOps and capacity planning for AI workloads
- Familiarity with enterprise Kubernetes distributions (OpenShift or equivalent)
- Kubernetes certification (CKA, CKS) or coaching and upskilling experience
- Experience with SRE and DevOps teams in a regulated asset management or banking environment
Project details
- Start: flexible
- Remote: onsite
- Location: Paris, France, FR
- Languages: French
Indexiert von der 9am-Meta-Suche. Du bist Job-Anbieter? Listing beanspruchen oder verwalten
Gefunden auf collective.work