Description
Job Summary
We're seeking a Platform Engineer (I3) who is an AI-native builder, someone who doesn't just use AI tools but designs and deploys AI agents to eliminate toil, accelerate developer workflows, and multiply what a lean team can deliver.
Responsibilities
- AI-Agent Development: Design, build, and iterate on AI agents that automate platform operations, from service and infra bootstrap, intelligent incident diagnosis, automated runbook execution, to self-healing infrastructure and PR-review bots. Own the agent lifecycle: prompt engineering, tool/function-call orchestration, evaluation, and production monitoring.
- Workflow Automation with AI: Identify and eliminate repetitive human-in-the-loop workflows across CI/CD, environment management, access provisioning, and change management.
- Developer Self-Service: Evolve our developer control plane (Cortex) into an AI-augmented self-service platform where engineers interact with intelligent assistants, not just dashboards, to scaffold services, debug deployments, query platform health, and resolve issues without filing tickets.
- Delivery & GitOps: Implement and maintain GitOps-based continuous delivery with Argo CD, integrating AI into CI pipelines for intelligent test selection, automated config validation, and deployment risk scoring.
- Kubernetes Infrastructure: Operate and evolve our Kubernetes platform on AWS EKS, focusing on environment hygiene, security, and cost efficiency, leveraging AI for anomaly detection, capacity recommendations, and automated remediation.
- Observability & Operational Excellence: Strengthen reliability by monitoring SLOs/error budgets and utilizing Datadog for metrics, traces, and logs, building AI-driven alerting and root-cause-analysis agents that reduce mean-time-to-resolution.
- Service Standardization: Maintain service scaffolds and templates that encode standards for testing and telemetry, using AI to auto-generate and validate configurations against platform baselines.
Requirements
- Bachelor's or Master's degree in Computer Science, Engineering, or a related field.
- 3+ years in platform, infrastructure, or backend engineering with deep knowledge of Kubernetes (EKS) and cloud-native architectures on AWS.
- Demonstrated experience building AI agents or agentic workflows, not just using Copilot or ChatGPT, but designing multi-step AI systems that autonomously perform operational tasks.
- A track record of automating repetitive workflows with AI.
- Experience in GitOps (ArgoCD) and CI (GitHub Actions) for multi-service systems.
- Strong coding skills in Go and/or Python, treating infrastructure as software.
- Excellent communication skills; able to clearly convey technical problems and advocate for both team and customer needs.
- Experience with LLM orchestration frameworks and prompt engineering for production systems.
Benefits
EarnIn offers excellent employee benefits, including healthcare, internet and cell phone reimbursement, a learning and development stipend, and potential opportunities to travel to our headquarters in Mountain View.