AI Agent Platform Engineer – Cloud Infra (Multi-Cloud)

Orbis; McLean (VA); Hybrid; USD 150,000 - 230,000; Full time

Benefits offered by this job

Competitive retirement matching

Paid time off

Job summary

Orbis is building the agentic AI capability its mission support operations rely on, with the AI Agent Engineer shaping both the core workflows and the cloud platform that runs them. You’ll own the footprint across GCP, Cloudflare, and Azure, manage it as code, and ensure security posture and cost controls scale as volume grows.

The role blends design and operations: 60% common core workflow engineering and 40% cloud infrastructure focus, requiring collaboration with process owners and strong

Qualifications

• 5+ years of proven experience translating user requirements into wireframes, workflows and such.
• 1+ year proven experience utilizing Claude or similar commercial offering to build AI agents.
• Experience building multi-agent workflows with clear design rationale and handoff
• Proficiency in prompt engineering including retrieval-augmented generation (RAG) and tool/callable functions
• Ability to explain technical work to non-technical audiences and elicit stakeholder requirements
• Experience troubleshooting agent workflows on Claude, GPT-class models, LangChain, AutoGen, or CrewAI
• Hands-on with APIs and scripting to build/debug workflows; coding experience not required but JSON payloads must not be blockers
• Sound judgment about model output and willingness to state when outputs should not be trusted
• Strong written communication for runbooks, docs, and reports
• Production experience with at least one major cloud platform (GCP/Azure/Cloudflare) and familiarity with a second
• Experience with infrastructure as code (Terraform, Pulumi) and cloud networking/identity/secrets management

Responsibilities

• Design, build, and deploy agentic AI workflows; create multi-agent and automated workflows for triage, data retrieval, summarization, reporting, and escalation routing.
• Explain system behavior to non-technical stakeholders using clear, actionable terms; translate plain-language process descriptions into workflow specs.
• Collaborate with process owners to ensure capabilities fit their operations; push back when requirements won't survive production.
• Maintain production reliability by monitoring workloads, diagnosing failures across prompts, tools, data, and orchestration.
• Own execution cost; optimize prompts, caching, or deterministic steps to control costs as volume grows.
• Set quality standards for AI outputs, incl. human review checkpoints and escalation criteria.
• Document builds via runbooks and SOPs that are accessible beyond one person.
• Integrate workflows across Orbis products (Catalyst, Pulse, Discovery) with engineering support.
• Deliver leadership-facing reports on metrics like resolution/escalation rates and timely data exports.
• Identify and close capability gaps; track advancements in agentic AI tooling and enterprise automation

Job description

Orbis is building the agentic AI capability its mission support operations rely on, with the AI Agent Engineer shaping both the core workflows and the cloud platform that runs them. You’ll own the footprint across GCP, Cloudflare, and Azure, manage it as code, and ensure security posture and cost controls scale as volume grows.

The role blends design and operations: 60% common core workflow engineering and 40% cloud infrastructure focus, requiring collaboration with process owners and strong