Platform Engineer

NextDay AI is a leading private company focused on applying artificial intelligence and creative innovation to B2C entertainment products. Our mission centers on harnessing Large Language Models (LLM) and generative AI to develop cutting-edge consumer experiences that redefine entertainment and companionship. Joining us offers a unique chance to contribute meaningfully to shaping the future of AI-driven consumer applications.

We are seeking a Platform Engineer to join our Platform team, which manages the infrastructure supporting our AI-powered consumer products. This team oversees a large, multi-provider GPU inference fleet, the routing layer, Kubernetes (EKS) clusters, observability, CI/CD pipelines, and incident management. The platform powers services used by millions of users daily.

This role suits a mid-level to senior engineer passionate about managing production systems at scale and enhancing automation. The position involves hands-on work such as provisioning and tuning GPU inference nodes, evolving the HAProxy routing layer, migrating infrastructure to Terraform and GitOps, improving deployment pipelines, and building dashboards and alerts to proactively manage incidents. We value engineers who take full ownership of problems and drive solutions independently.

Key Responsibilities

- Operate and expand the GPU inference fleet across multiple providers, including bare-metal, rented, and cloud GPU nodes. Tasks include provisioning with Ansible, deploying and tuning inference engines, and integrating nodes into the routing layer.
- Develop automation for capacity management, including scheduled pre-warming and metric-driven scaling of elastic GPU nodes and hosted endpoints to replace manual scaling during peak periods.
- Manage EKS clusters, including ArgoCD, Cluster Autoscaler, CoreDNS, and load balancer controllers, handling version upgrades and resource right-sizing.
- Operate ECS clusters using Terraform and AWS integrations.
- Enhance CI/CD workflows on GitHub Actions to enable faster pull request checks and safer, more frequent production deployments.
- Expand observability capabilities by creating Grafana dashboards and alert rules, defining Prometheus metrics for GPU nodes and proxies, managing structured logging with Fluent Bit and Axiom, and implementing per-request cost attribution.
- Support FinOps initiatives by tracking inference and cloud spending, identifying cost-saving opportunities such as right-sizing and provider optimization, and converting findings into actionable tickets.
- Document runbooks, architecture, and operational decisions in Confluence to ensure knowledge sharing across the team.

Required Qualifications

- Minimum of 3 years’ experience as a Platform, DevOps, SRE, or Infrastructure Engineer managing production systems in startup or scale-up environments.
- Proficient with Kubernetes, preferably AWS EKS, including GitOps deployments (e.g., ArgoCD) and cluster lifecycle management (upgrades, autoscaling, node groups).
- Strong AWS expertise covering EC2, VPC, networking, load balancers (ALB/NLB), IAM, CloudWatch, and S3, with the ability to analyze cloud billing.
- Skilled in Infrastructure as Code using Terraform and configuration management with Ansible.
- Solid Linux and networking fundamentals, including systemd, nftables/iptables, DNS, TLS certificates, SSH, and troubleshooting using logs and metrics.
- Experience with observability tools such as Prometheus and Grafana (dashboards, alert rules, PromQL) and structured logging pipelines (Fluent Bit, Axiom).
- CI/CD experience with GitHub Actions, including pipeline development and maintenance.
- Proficient scripting and tooling skills in Go, Python, or TypeScript, capable of building small services and CLI tools for automation beyond shell scripting.
- Regular hands-on use of AI coding tools (e.g., Claude Code, Cursor, Copilot) for coding, debugging, and documentation, with an understanding of their strengths and limitations.
- Interest in promoting effective AI tool adoption among engineers by developing shared skills, prompts, integrations, and guardrails.
- Experience supporting GPU workloads.
- Familiarity with serverless and event-driven AWS services such as Lambda, Serverless Framework, DynamoDB, SQS, and EventBridge.
- Clear written communication skills for documenting runbooks, decisions, and analyses in Confluence and Jira.

Preferred Qualifications and Benefits

- Fully remote work environment with no physical office attendance required.
- Flexible scheduling with a focus on teamwork and results.
- Unlimited vacation policy.
- Dynamic and supportive workplace culture.
- Opportunity to collaborate closely with company owners and leaders in a fast-growing AI-focused organization.
- Work at scale managing a GPU fleet serving LLM traffic to millions of users, directly impacting product reliability and cost efficiency.

If you are passionate about AI innovation and want to be part of a pioneering team shaping the conversational AI revolution, we encourage you to apply and join us on this exciting journey.