AI Agent Engineer: Client Experience & Onboarding

Orbis; McLean (VA); On-site; USD 140,000 - 190,000; Full time

Job summary

Orbis is building the agentic AI capability its mission support operations run on, and the AI Agent Engineer builds and operates it. Sixty percent of this role is common to every AI Agent Engineer at Orbis: designing, building, and deploying the multi-agent workflows behind triage, data retrieval, summarization, reporting, and escalation routing.

The remaining forty percent is this role's focus — owning how clients get support on Orbis products already in the field.

Qualifications

• Must have 5 years proven experience translating user requirements into wireframes, workflows and such.
• Must have 1-year proven experience utilizing Claude or similar commercial offering to build AI agents.
• Demonstrated experience building a functioning multi-agent workflow, with the ability to walk through the design rationale, how the agents hand off work and share context, what broke, and how it was fixed.
• Practical command of prompt engineering, including retrieval-augmented generation (RAG) and tool or function calling.
• Proven ability to explain technical work to non-technical audiences — describing a system's behavior, limits, and failure modes to a process owner or executive without hedging or retreating into jargon.
• Demonstrated ability to elicit requirements from stakeholders who cannot hand over a specification, and to reach a working solution regardless.
• Ability to troubleshoot agent workflows built on platforms such as Claude, GPT-class models, LangChain, AutoGen, or CrewAI, and to isolate whether a failure originates in the prompt, the tool, the data, or the orchestration.
• Working proficiency with APIs and sufficient scripting ability to build and debug workflows independently; JSON payload or a Python script must not be a blocker.
• Sound judgment about model output, including the discipline to state plainly when an output should not be trusted.
• Strong written communication. This role produces documentation, runbooks, and reports that program leads and executives rely on.
• Experience building and operating external-facing interfaces, portals, or client-facing applications in production.
• Experience designing or automating customer onboarding and provisioning.
• Experience designing support workflows — intake, triage, escalation, resolution — and instrumenting them so performance is measurable.

Responsibilities

• Design, build, and deploy agentic AI workflows.
• Explain systems to non-technical stakeholders in clear terms and translate process descriptions into workflow specs.
• Collaborate with process owners to tailor capabilities to their operations.
• Monitor production workloads and diagnose failures across prompts, tools, data, and orchestration.
• Own cost of execution and optimize prompts or caching to control costs.
• Define accuracy standards and escalation criteria with checks for proof.
• Document runbooks and SOPs to enable others to operate workflows.
• Integrate workflows with Orbis products (Catalyst, Pulse, Discovery).
• Deliver reporting on resolution and escalation metrics and export data as needed.
• Identify capability gaps and coordinate with engineering to close them.

Skills

Wireframes & workflows

Claude AI

Multi-agent systems

Prompt engineering

APIs scripting

Stakeholder communication

External-facing interfaces

Production support

Monitoring & debugging

Tools

Claude

LangChain

AutoGen

CrewAI

Job description

Orbis is building the agentic AI capability its mission support operations run on, and the AI Agent Engineer builds and operates it. Sixty percent of this role is common to every AI Agent Engineer at Orbis: designing, building, and deploying the multi-agent workflows behind triage, data retrieval, summarization, reporting, and escalation routing.

The remaining forty percent is this role's focus — owning how clients get support on Orbis products already in the field.