Agentic AI Orchestration Architect

Aquent is proud to partner with a leading innovator in visual production, a company renowned for its commitment to exceptional design and delivering high-quality visual experiences. This organization is at the forefront of leveraging cutting-edge technology to streamline creative workflows and enhance efficiency. They are seeking visionary talent to join them in transforming their production landscape.

Unleash Your Expertise as an Agentic AI Orchestration Architect!

Imagine shaping the future of creative production by building intelligent systems that empower a dynamic Visual Production team. We are looking for an exceptional **Agentic AI Orchestration Architect** to join our client for a pivotal short-term engagement. This is your chance to make a profound impact, designing and implementing a robust orchestration layer that seamlessly connects existing agents, automations, applications, and human-driven workflows. You'll be instrumental in creating a system where every stage retains its integrity, human review is optimized, and value is delivered incrementally, ensuring immediate, tangible benefits. If you're passionate about leveraging AI to solve complex workflow challenges and thrive on seeing your architectural designs come to life in daily production, this role offers an unparalleled opportunity to innovate and lead.

Your Impactful Contributions Will Include:

• Confirming current Visual Production workflows, systems, assets, handoffs, approvals, exceptions, open decisions, and bottlenecks, identifying critical rules for team resolution.
• Identifying authoritative systems for job state, assets, approvals, and final outputs, then documenting the target workflow and a strategic milestone plan for the first release.
• Designing a canonical work-order schema and a durable state model encompassing job ID, assets, references, asset/version lineage, routing, status, ownership, approvals, decisions, and comprehensive audit history.
• Building the core orchestration layer to track job and stage state, intelligently route work within and between user workflows, collect outputs, trigger downstream processes, and proactively identify stalled or blocked jobs.
• Supporting stage-level human review, revision, and manual completion events, ensuring work advances only upon required approvals or completion signals, including crucial physical production steps like studio shoots and print proofs.
• Developing conditional routing mechanisms based on job state and asset readiness, enabling stages to be bypassed when assets already exist, and safely propagating upstream changes to affected downstream work.
• Connecting existing agents, automations, and systems through APIs, webhooks, and other appropriate interfaces, automating file and status handoffs across tools like Google Workspace, Box, Figma, and shared file repositories.
• Building for reliability and delivering in incremental production milestones, releasing working capabilities into daily use as they are ready, and continuously refining with team feedback, documentation, and training.

Deliverables You Will Create:

• **Workflow Architecture:** Current- and target-state specifications, comprehensive architecture diagrams, a canonical work-order schema, a robust state model, and a strategic milestone plan for sequencing capabilities into incremental releases.
• **Working Orchestration Layer:** Delivered in production milestones, starting with a first release on live jobs as soon as dependencies allow, and expanding to include conditional routing, stage-level approvals, manual completion events, downstream change propagation, and sophisticated exception handling.
• **Integrations and Visibility:** Agreed agents and systems connected through stable interfaces, providing clear visibility of job status, ownership, asset/version lineage, approval, and decision history across all handoffs.
• **Handoff:** Comprehensive documentation, a detailed runbook, thorough training, and a prioritized backlog sufficient for the client team to seamlessly operate, troubleshoot, and extend the system independently.

What You Bring:

To thrive in this role, you will possess a unique blend of technical prowess, strategic thinking, and a passion for optimizing complex workflows. We are looking for:

• 5+ years of experience building production software, creative technology, automation, integration, or workflow systems, with recent hands-on agentic AI experience.
• Demonstrated experience deploying production agentic or multi-agent workflows, with the ability to articulate their architecture, reliability model, and operating approach.
• Strong workflow and state-machine design skills, including conditional routing, shared state, human-in-the-loop processes, events, retries, and idempotency.
• Hands-on Python or TypeScript development expertise with REST APIs, webhooks, OAuth, structured outputs, and JSON schemas.
• Experience with agent/tool interoperability patterns, including MCP or equivalent approaches.
• Production experience developing OpenAI agents; comparable experience with other production agent platforms is also highly valued.
• Hands-on integration experience with Google Workspace APIs (Drive, Slides), Box, and shared file-server or DAM environments; Figma API experience is preferred.
• Ability to design model- and framework-agnostic systems using stable interfaces, avoiding tight coupling to any single agent, model, or vendor.
• Solid security fundamentals and experience navigating enterprise IT and security reviews for AI and workflow integrations, including least-privilege access, credential management, third-party systems, and confidential assets.
• Proven experience translating nontechnical team workflows into usable systems and delivering fixed-scope engagements incrementally through production milestones, comprehensive documentation, training, and effective handoff.

Nice-to-Have Skills That Will Set You Apart:

• Creative operations or production-tracking experience across image generation, retouching, 3D/rendering, DAM, or other large-asset workflows.
• Familiarity with workflow automation platforms such as n8n, Make, Zapier, or equivalent.
• Experience with agent interoperability approaches and orchestration frameworks such as A2A, LangGraph, Google ADK, or similar.
• Comfort learning automation interfaces for creative tools such as Photoshop, 3ds Max, Figma Weave, and ComfyUI; scripting, Google Apps Script, or agent observability experience is a plus.