Cloud Platform Engineer

This is a fully remote position, open to applicants in Alabama.

📋 Description

• Manage and enhance a Kubernetes-based platform designed for AI workloads, which includes LLM gateways, agent and tool-integration gateways, and agent runtimes.

• Integrate and oversee access to cloud-hosted foundation models from various providers, ensuring efficient routing, quotas, fallbacks, cost management, and tenant isolation.

• Provide infrastructure as code and implement GitOps workflows.

• Develop monitoring, alerting, and tracing solutions for AI workloads.

• Assist in designing and prototyping self-hosted model serving, taking into account GPU workloads and inference runtimes.

• Strengthen the platform with robust secrets management, network policies, authentication and authorization controls, and audit logging.

• Offer support to internal product teams through comprehensive documentation, onboarding, and troubleshooting assistance.

⛳️ Requirements

• A minimum of 3 years of experience in platform engineering, DevOps, SRE, or cloud engineering.

• Practical experience with Kubernetes, including deployments, networking, and troubleshooting.

• Proficient in infrastructure as code utilizing Terraform.

• Familiarity with GitOps tools such as Argo CD, Flux, or similar solutions.

• Strong experience with at least one major cloud provider, either Azure or AWS.

• Knowledge of observability tools like OpenTelemetry, Prometheus, and Grafana.

• Competence in scripting and coding languages such as Python, Go, or Bash.

• Experience with CI/CD processes.

• Familiarity with LLM gateways or proxies, as well as LLM observability and tracing tools.

• Understanding of managed model services from leading cloud providers, such as Azure or AWS.

• Comprehension of agent frameworks and tool-integration protocols, including Model Context Protocol (MCP).

• Experience in executing GPU workloads or model inference serving.

• Background in multi-tenant, regulated, or compliance-oriented environments.

🏝️ Benefits

• Opportunities for professional development.

• Reimbursement for training and ongoing education.

• Modern, open office spaces.

• Complimentary lunches provided.

• Fully stocked kitchens available.

• Comprehensive wellness initiatives.

• Flexible time-off programs.

• Benefits for family formation.

• Support for family-building efforts.

• Paid volunteer time off.

• Donation matching program.