About this role
Scaling the internal developer platform requires eliminating manual configuration bottlenecks through intelligent automation, ensuring product teams can ship code swiftly and securely. EarnIn seeks a Senior AI Platform Engineer to design, build, and operate agentic systems and core infrastructure that transition the platform from static management to AI-augmented orchestration.
Working within the Platform-as-a-Service Engineering group, this person will develop AI agents capable of handling incident triage, environment provisioning, and configuration generation. Ideal candidates combine deep cloud infrastructure expertise with practical experience deploying production-ready AI agents and LLM integrations to reduce operational toil.
What you will do
- Design, build, and operate production-ready AI agents while following governance standards for model safety, evaluation, and selection.
- Implement agentic patterns for cloud infrastructure and contribute to infrastructure-as-code practices that version prompts and evaluation criteria.
- Operate and scale high-availability distributed systems on AWS, resolving performance and stability bottlenecks.
- Contribute to the developer control plane to create an AI-augmented self-service platform supporting natural language debugging and service scaffolding.
- Support and mentor less experienced engineers on prompt engineering, LLM integration, and agentic workflows.
- Participate in on-call rotations and use post-mortems to refine system reliability and automated remediation.
What you need
- Hold a Bachelor's or Master's degree in Computer Science, Engineering, or a related technical field.
- Bring at least four years of experience in cloud infrastructure working on large-scale, high-availability distributed systems.
- Possess hands-on experience building and operating AI-driven systems and agentic workflows in production environments.
- Demonstrate strong working knowledge of AWS services, containerized architectures, and Kubernetes at scale.
- Show proficiency in infrastructure-as-code tools and strong coding abilities in Python or Go.
- Understand security, privacy, and compliance best practices regarding production AI systems, including prompt injection prevention and data isolation.
Nice to have
- Experience building AI-driven alerting or root-cause analysis systems
- Experience with service mesh and traffic management at scale
- Proficiency with GitOps and CI/CD orchestration tools
- Experience with MLOps or LLMOps concepts
- Familiarity with security frameworks relevant to AI systems
Benefits
- Equity
- Benefits
Skills and tech stack
Questions candidates ask
What is the work location policy for this position?
This is a hybrid position based at the headquarters in Mountain View, requiring in-office work two days a week.
What is the salary range for the role?
The base salary range for this full-time position is $228,000 to $279,000, plus equity and benefits, with exact placement determined by role, level, and location.
What technologies will I be working with?
The stack includes AWS, EKS, ArgoCD, GitHub Actions, Cortex, Terraform, Ansible, Datadog, Python, Go, and various LLM orchestration frameworks.
What kind of tasks will the AI agents handle?
The agents will handle real slices of incident triage, environment provisioning, config generation, and developer self-service to reduce operational toil.