AI Agent Infra Engineer, Multi-Cloud Platform

Orbis; Washington (District of Columbia); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Competitive retirement matching

PTO policy with real time off

Job summary

Orbis is building a cloud-first AI agent platform that runs triage, data retrieval, and reporting across GCP, Azure, AWS, and Cloudflare. The role focuses on designing scalable multi-agent workflows and managing secure, cost-aware infrastructure as code.

You will translate stakeholder needs into production-grade workflows, monitor reliability, and partner with product teams to ensure solutions fit real operations while remaining within budget and security standards.

Qualifications

• Must have 5 years translating user requirements into wireframes, workflows and such.

Responsibilities

• Design, build, and deploy agentic AI workflows including triage, data retrieval, summarization, reporting, and escalation routing.
• Explain systems to non-technical stakeholders and turn plain-language process descriptions into workflow specs.
• Collaborate with process owners to tailor capabilities to operations; push back when needed.
• Monitor production, diagnose failures across prompts, tools, data, and orchestration; know when to involve engineering.
• Own cost of execution; identify caching or deterministic steps to save money as volume grows.
• Define quality standards, human review checkpoints, and escalation criteria for automated workflows.
• Document runbooks and SOPs for operations and troubleshooting.
• Integrate workflows across Orbis products like Catalyst, Pulse, and Discovery.
• Deliver leadership dashboards and recurring reports on KPIs like resolution and escalation rates.
• Identify and close capability gaps; keep up with agentic AI tooling and enterprise automation trends.

Skills

Requirements translation and workflows

Prompt engineering

Explain technical work to non-tech

Stakeholder elicitation

Troubleshoot AI workflows

APIs scripting

Cloud platform experience

Cost and security awareness

Tools

Claude

LangChain

AutoGen

CrewAI

Python scripting

Job description

Orbis is building a cloud-first AI agent platform that runs triage, data retrieval, and reporting across GCP, Azure, AWS, and Cloudflare. The role focuses on designing scalable multi-agent workflows and managing secure, cost-aware infrastructure as code.

You will translate stakeholder needs into production-grade workflows, monitor reliability, and partner with product teams to ensure solutions fit real operations while remaining within budget and security standards.