A
AI Operations Engineer
On-siteFull-timeAI EngineeringCreative SoftwareEnterprise Software
Build and operate the internal AI and automation infrastructure that supports teams across a global creative technology company. Own platform reliability, identity controls, cloud infrastructure, CI/CD, security, cost management, and safe deployment of AI assistants and workflows.
Responsibilities
- Own the full lifecycle of internal AI and automation platforms, including runtime infrastructure, CI/CD, and identity controls
- Implement identity boundaries, access controls, cost management, and operational efficiency measures
- Design and operate automations and custom AI assistants for internal teams
- Evaluate emerging models, agent frameworks, and SaaS tools and onboard suitable solutions
- Establish reusable design patterns, integrations, and prompt libraries for safe and efficient automation
Requirements
- At least 3 years of experience in DevOps, SRE, or production engineering
- Coding and scripting experience for automation, API integrations, and internal tooling
- Hands-on experience with Terraform, Docker, CI/CD pipelines, and secrets management
- Practical knowledge of OAuth2, SSO/SCIM, REST APIs, webhooks, and scoped service accounts
- Hands-on experience with LLMs, including Claude or ChatGPT APIs, prompt engineering, MCPs, and plugins
- Experience managing and architecting AWS cloud infrastructure
- Ability to translate non-technical stakeholder needs into safe, effective automations
Nice to have
- Experience with workflow and automation platforms such as n8n, Temporal, Workato, Make, or Hermes
- Exposure to AI gateway or routing layers such as LiteLLM, OpenRouter, or Bedrock
- Familiarity with vector databases, retrieval-augmented generation, or LLM observability tools
- Background in IT infrastructure or corporate systems automation