Senior Infrastructure Engineer, Self-Hosted AI Platform

Serval; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Impact

Growth

Culture

Job summary

Serval is building an AI platform to automate complex IT workflows for modern enterprises. As a Software Engineer, Infrastructure, you'll scale foundational systems powering Serval's AI agents and enable on-premises deployments for enterprises.

You will design distributed architectures, write Terraform modules, and build deployment templates to support self-hosted environments alongside cloud deployments.

Qualifications

• 3+ years building and operating large-scale distributed systems.
• Strong experience writing Terraform for infrastructure provisioning and management.
• Deep knowledge of AWS, GCP, or Azure.
• Experience building, packaging, and supporting self-hosted deployments for enterprise customers.
• Proficiency in Python, Go, or similar languages for automation and tooling.
• Strong understanding of networking, databases, containers, and orchestration.
• Experience with monitoring, logging, alerting and incident management tools.
• Ability to communicate technical concepts clearly to customers.

Responsibilities

• Design, implement, and operate large-scale distributed systems powering Serval's AI agents and data pipelines.
• Write and maintain Terraform modules to provision cloud infrastructure across AWS, GCP, or Azure.
• Build and maintain deployment packages and templates for self-hosted deployments.
• Provide technical guidance and troubleshooting for enterprise self-hosted deployments.
• Ensure high availability, performance, and reliability of production systems through monitoring and incident response.
• Build internal tools to enable product engineers to deploy and operate services.
• Collaborate with engineering to design scalable architectures for cloud and self-hosted models.
• Profile and optimize compute, storage, networking, and database layers.
• Implement security best practices and enterprise compliance for deployments.

Skills

Python

Go

Distributed systems

Networking

Containerization

Incident management

Communication

Tools

Terraform

Docker

Kubernetes

AWS

GCP

Azure

Datadog

Prometheus

Grafana

PagerDuty

Job description

Serval is building an AI platform to automate complex IT workflows for modern enterprises. As a Software Engineer, Infrastructure, you'll scale foundational systems powering Serval's AI agents and enable on-premises deployments for enterprises.

You will design distributed architectures, write Terraform modules, and build deployment templates to support self-hosted environments alongside cloud deployments.