Job Specifications
About Intent HQ
About Intent HQRecognised by the Financial Times as one of the FT1000 Fast Growing Companies in Europe (2022–2024), and winners of both Analytics Company of the Year 2025 and AI Company of the Year 2024 at the British Data Awards, Intent HQ is a leader and innovator in Customer AI Analytics and Data Science. Backed by strong investors and trusted by a blue-chip international enterprise customer base, our mission is to become the world’s preeminent Customer Intent Engine by combining privacy-first signal intelligence, proprietary behavioural AI/ML analytics, and uniquely accessible enterprise insights into a single platform that enables organisations to build more genuine, sustainable, and profitable relationships with customers.
We began by solving complex challenges for clients in the telecommunications sector, including Verizon, O2, and Orange, and have since expanded into Financial Services, Retail, and Social Media, with clients such as HB Reavis and Zurich Group. Our clients typically manage tens of millions of customers and process billions of interactions daily. Our platform is purpose-built to handle data at this enormous scale efficiently, delivering tangible results
What sets us apart is our focus on deep customer interaction data, doing the hard, specialised work so our clients can focus on applying insight to their business strategies.
Today, Intent HQ is home to an exciting, diverse, and fast-growing team of 100+ people across London, Barcelona, Lisbon, Tel Aviv, New York, South Africa & India, collectively speaking over 15 languages.
Recent Awards & Recognition:
Best AI Ethics & Diversity Award 2025 - AI World Series Awards
AI Business of the Year 2025 - The National AI Awards
Analytics Company of the Year 2025 – British Data Awards
AI Company of the Year 2024 – British Data Awards
FT1000 Europe’s Fastest Growing Companies 2022–2024 – Financial Times & Statista
Top 100 Edge Computing Company 2024 – STL Partners
Why Join Us:
Exciting Work Environment: Work on cutting-edge technology at the intersection of AI and data analytics.
Impactful Role shaping how the company moves forward
Growth Opportunities: Advance your career in a fast-paced, innovative industry
Hybrid role: 3 days per week in our state-of-the-art London office plus access to the onsite gym (including towel serviced showers and changing facilities)
The Opportunity
The AI Orchestration Architect is a hybrid business & technical role responsible for designing, implementing, orchestrating and optimising intelligent AI systems composed of agents, workflows and prompts. This role sits at the intersection of multi-agent orchestration, workflow design, prompt engineering and system reliability.
You will translate ambiguous human goals into precise AI instructions, architect reusable prompt and agent frameworks, and ensure that AI agents collaborate safely, predictably, and efficiently at scale. Acting as both a linguistic architect and a systems orchestrator, you will enable reliable human–AI and agent–agent workflows across the organisation.
This role is critical to scaling AI-driven automation while maintaining clarity, safety, and performance in a rapidly evolving ecosystem.
Key Responsibilities
Agent Network & Workflow Orchestration
Design, configure, and maintain AI agent networks, including roles, capabilities, scopes, and handoff logic.
Define how prompts, tools, agents, and humans interact within end-to-end systems.
Ensure agents are aligned with business goals and operate within clear boundaries.
Implement modular, reusable agent components across workflows.
Interaction Protocols & Governance
Define interaction rules between agents (communication patterns, delegation logic, escalation paths).
Establish guardrails, validation steps, and safety mechanisms for agent-to-agent and agent-to-human interactions.
Maintain clear documentation of protocols, decision logic, and system diagrams.
Promote responsible AI use, including bias mitigation and safe output practices.
Prompt & Agent Framework Management
Build and maintain centralised prompt and agent libraries.
Develop versioning, testing, and evaluation frameworks for prompts and agents.
Maintain auditable records of changes, experiments, and system decisions.
Ensure adherence to organisational standards for quality, safety, and performance.
Prompt Engineering & Instruction Architecture
Design sophisticated prompt chains for multi-step and multi-agent workflows.
Translate human requirements into structured, high-reliability AI instructions.
Create reusable prompt templates, patterns, macros, and system messages.
Optimise prompt clarity, constraints, and instruction hierarchies to drive consistent outputs.
Monitoring, Evaluation & System Health
Monitor real-time agent behaviour, workflows, and cross-agent dependencies.
Detect emergent behaviours—both beneficial and risky—and intervene when systems deviate from expectations.
Track system health metrics, fail