Platform Engineer (GPU Inference, EKS, Terraform)

About the role

NextDay AI is a privately held company building consumer AI products powered by large language models and generative AI. It is looking for a Platform Engineer to join its Platform team, which owns the infrastructure behind its consumer AI products: a large multi-provider GPU inference fleet, its HAProxy routing layer, EKS clusters, observability, CI/CD and incident management. The role suits a mid-level or senior engineer who likes hands-on work on production systems at scale and raising automation.

Key responsibilities

• Provision and tune GPU inference nodes, evolve the HAProxy routing layer and move infrastructure into Terraform and GitOps
• Build automation for capacity management, such as scheduled pre-warming and metric-driven scaling of GPU nodes and endpoints
• Operate EKS clusters (ArgoCD, Cluster Autoscaler, CoreDNS, load balancer controller) and ECS clusters, including upgrades and right-sizing
• Improve CI/CD on GitHub with faster PR checks and safer production deploys
• Extend observability with Grafana dashboards, Prometheus metrics, structured logging (Fluent Bit, Axiom) and per-request cost attribution
• Contribute to FinOps by tracking inference and cloud spend and turning savings into tickets
• Document runbooks, architecture and decisions in Confluence

Required profile

• 3+ years as a Platform, DevOps, SRE or Infrastructure Engineer in a startup or scale-up
• Experience running or supporting GPU workloads
• Hands-on use of AI coding tools (e.g. Claude Code, Cursor, Copilot) and interest in helping others adopt them
• Clear written communication, documenting in Confluence and Jira

Required skills

• Kubernetes on AWS EKS, GitOps (ArgoCD), cluster lifecycle operations
• AWS: EC2, VPC, ALB/NLB, IAM, CloudWatch, S3, Lambda, DynamoDB, SQS, EventBridge
• Terraform and Ansible
• Prometheus, Grafana, PromQL, Fluent Bit, Axiom
• GitHub Actions pipelines
• Go, Python or TypeScript for automation scripts and CLIs

What we offer

• 100% remote work
• Flex-time policy
• Unlimited vacation policy
• A dynamic, supportive environment in a fast-growing AI company