IT DevOps Engineer

Fireworks AI operates an AI platform for production inference and training of open-source models.

San Mateo, United States
About Fireworks AI

Fireworks AI provides serverless and dedicated model inference, model deployment, and supervised and reinforcement fine-tuning for developers and enterprises building AI applications.

View jobs by Fireworks AI

Skills

Candidate Availability

Required and preferred rules are kept separate and reflect the wording in the original posting.

About the Role

You will build and operate automation workflows, integrations, and delivery infrastructure. You will own API integrations, automate operational runbooks, provision cloud environments, support model deployment pipelines, and make failures visible through observability, retry, fallback, escalation, and current documentation.

Requirements

  • 6+ years building production systems
  • Strong Python plus JavaScript or TypeScript
  • Workflow orchestration expertise with n8n, Temporal, Make, or a comparable platform
  • REST, GraphQL, webhooks, gateways, proxying, and API authentication knowledge
  • CI/CD ownership with GitHub Actions, GitLab CI, or Jenkins
  • Production Kubernetes experience on AWS or GCP
  • Terraform experience
  • Cross-team technical ownership

Responsibilities

  • Design, deploy, and maintain mission-critical workflows
  • Replace manual operational runbook steps with event-driven workflows
  • Build custom nodes, webhooks, and functions
  • Design and secure REST, GraphQL, and webhook integrations
  • Handle rate limits, retries, backpressure, and payload validation
  • Mock, test, and version APIs
  • Co-own CI/CD pipelines for model and infrastructure deployments
  • Provision multi-cloud environments using infrastructure as code
  • Package and scale GPU and CPU workloads on Kubernetes
  • Instrument pipelines and workflows with observability tooling
  • Build self-healing retry, fallback, and escalation paths
  • Maintain workflow maps and runbooks

Benefits

  • Equity