SRE for AI Infra & Multi-Cloud Platform

Mithril; Palo Alto, Northern (CA, KY); Hybrid; USD 170,000 - 230,000; Full time

Benefits offered by this job

Health, dental, and vision coverage

401k with company match

14 company holidays; including 2 float

Job summary

Mithril is seeking an experienced Site Reliability/Infrastructure Engineer to scale its GPU orchestration platform across multiple clouds. You will own reliability, automation, observability, and tooling, collaborating with the founding team on capacity planning and SLO design.

You will build infrastructure as code, automate operations with Python or Go, and help manage GPU capacity while shaping how Mithril delivers fast, reliable access to its platform.

Qualifications

• 3+ years in SRE/Production Engineering/Infrastructure at a high-growth tech company.
• Hands-on Kubernetes: clusters, deployments, multi-tenant environments.
• Cloud proficiency in AWS, GCP or Azure with networking basics.
• Proficiency in Python or Go to build tools and services.
• Strong Linux fundamentals and security best practices.
• Calm, rigorous RCA-focused troubleshooter with clear communication.

Responsibilities

• Platform reliability and infrastructure automation comprise ~70–75% of time.
• Own SLIs and SLOs for API and orchestration services; drive operability.
• Build dashboards, alerts and tracing for multi-cloud visibility.
• Develop Terraform/Pulumi modules and Kubernetes configurations.
• Automate health checks, capacity rebalancing and provider reconciliation.
• Assist GPU capacity management and data-driven supply decisions.

Skills

SRE experience

Kubernetes

Cloud platforms

Python or Go

Linux fundamentals

Troubleshooting

Communication

Tools

Terraform

Pulumi

Kubernetes configs

Python

Job description

Mithril is seeking an experienced Site Reliability/Infrastructure Engineer to scale its GPU orchestration platform across multiple clouds. You will own reliability, automation, observability, and tooling, collaborating with the founding team on capacity planning and SLO design.

You will build infrastructure as code, automate operations with Python or Go, and help manage GPU capacity while shaping how Mithril delivers fast, reliable access to its platform.