Infrastructure Engineer – Self-Hosted AI Platform

Serval, Inc.; San Francisco (CA); On-site; USD 190,000 - 240,000; Full time

Job summary

Serval, Inc. is building an AI-native automation platform. We are seeking a Software Engineer, Infrastructure to design, implement, and operate large-scale distributed systems powering Serval's AI agents and workflow orchestration.

You will focus on self-hosted deployments for enterprise customers and maintain production-grade infrastructure. You will work with Terraform, Docker, and Kubernetes across AWS, GCP, or Azure, ensuring high availability, security, and scalable data pipelines.

Qualifications

• 3+ years building and operating large-scale distributed systems in production environments.
• Strong experience writing and maintaining Terraform for infrastructure provisioning and management.
• Deep knowledge of at least one major cloud provider (AWS, GCP, or Azure), including compute, networking, storage, and managed services.
• Experience building, packaging, and supporting self-hosted or on-premises software deployments for enterprise customers.
• Proficiency in Python, Go, or similar languages for building automation, tooling, and infrastructure services.
• Strong understanding of networking, databases, containerization (Docker, Kubernetes), and orchestration systems.
• Experience with monitoring, logging, alerting, and incident management tools (e.g., Datadog, Prometheus, Grafana, PagerDuty).
• Ability to communicate technical concepts clearly to customers and provide infrastructure support and guidance.
• Ability to debug complex system issues, analyze performance bottlenecks, and implement effective solutions.

Responsibilities

• Design, implement, and operate large-scale distributed systems that power Serval's AI agents, workflow orchestration, and data pipelines.
• Write and maintain Terraform modules to provision and manage cloud infrastructure across AWS, GCP, or Azure environments.
• Build and maintain deployment packages, installation scripts, and infrastructure templates that enable customers to self-host Serval in their own environments.
• Provide technical guidance and troubleshooting support to enterprise customers deploying and operating self-hosted instances of Serval.
• Ensure high availability, performance, and reliability of production systems through monitoring, alerting, incident response, and capacity planning.
• Build internal tools and platforms that enable product engineers to deploy, test, and operate services efficiently.
• Collaborate with engineering teams to design resilient, scalable architectures that support both cloud-hosted and self-hosted deployment models.
• Profile and optimize system performance, including compute, storage, networking, and database layers.
• Implement security best practices and ensure infrastructure meets enterprise compliance requirements for both managed and self-hosted deployments.

Skills

Distributed systems

Terraform

Cloud platforms

Python

Go

Networking

Containers

Monitoring

Debugging

Communication

Kubernetes in production

Tools

Terraform

Docker

Kubernetes

Datadog

Prometheus

Grafana

Job description

Serval, Inc. is building an AI-native automation platform. We are seeking a Software Engineer, Infrastructure to design, implement, and operate large-scale distributed systems powering Serval's AI agents and workflow orchestration.

You will focus on self-hosted deployments for enterprise customers and maintain production-grade infrastructure. You will work with Terraform, Docker, and Kubernetes across AWS, GCP, or Azure, ensuring high availability, security, and scalable data pipelines.