Solution Architect - Agent Catalogue

Job Title: Solution Architect - Agent Catalogue

Work Level: 2A

JOB PURPOSE

We are looking for a Manager, Agentic Solution Architecture & Reuse to provide hands-on solution architecture and technical design assurance for agentic artificial intelligence solutions across Unilever.

As agentic artificial intelligence adoption continues to scale across technologies and business domains, you will make sure our agentic solutions are secure, scalable, cost-efficient, reusable and future-fit. You will work across technology platforms rather than being tied to a single vendor stack, ensuring the right architecture, models, integration patterns, skills and governance controls are applied consistently as solutions move from experimentation into production and scale.

You will also anchor two critical enterprise capabilities: token and model optimisation, continuously improving the efficiency and cost of agentic workloads; and Agent Catalogue and Skill Registry hydration, making sure proven agents, skills and architecture patterns are captured, governed and reused across Unilever rather than repeatedly rebuilt.

You will work closely with product teams, engineers, platform teams, security, Enterprise Architecture and business stakeholders as part of the Hyper Automation Technical Design Authority.

Because here, we don’t just hire for jobs. We invite you to be part of something bigger.

KEY RESPONSIBILITIES

• undefined
• Provide solution architecture for artificial intelligence and agentic use cases across multiple technologies and platforms.
• Translate business requirements into robust technical architectures covering agents, models, skills and tools, data, integration and orchestration.
• Conduct technical design reviews and make sure solutions meet agreed architecture and engineering standards before progressing to build and production.
• Determine when requirements should be met through native platform capabilities, reusable enterprise capabilities or custom pro-code development, keeping architectures portable and avoiding unnecessary platform lock-in.
• Define and apply architecture patterns covering orchestration, grounding, agent-to-agent interaction, human-in-the-loop, application programming interfaces, Model Context Protocol (MCP) and tool integration, and deterministic automation.
• undefined
• Make sure agentic solutions are designed for enterprise scale rather than individual proofs of concept or isolated use cases.
• Assess designs for scalability, resilience, observability, maintainability, security and cost.
• Monitor the evolution of models, agent frameworks and platform capabilities, and determine where existing architecture patterns need to evolve.
• Partner with the Senior Manager, AI Solution Architecture and Enterprise Architecture to convert emerging approaches into approved reusable patterns.
• Support the progression of solutions towards greater autonomy while maintaining appropriate control, audit and human intervention points.
• undefined
• Embed security, privacy, Responsible AI and governance requirements directly into solution design.
• Make sure agent identity, permissions, data access, tool access and execution boundaries are appropriately designed.
• Maintain traceability of architecture decisions and exceptions, identify architectural risks early and drive remediation before production deployment.
• Make sure reusable assets have clear technical ownership and lifecycle accountability.
• undefined
• Anchor token optimisation across agentic workloads, analysing excessive context, prompts, agent interactions and model calls and recommending architectural optimisation.
• Drive patterns such as context reduction, better retrieval, reusable system instructions, efficient agent and tool interaction and right-sized model selection.
• Work with solution teams to improve cost per outcome, not simply model cost per token, and identify where smaller, lower-cost models can safely replace larger models for defined task classes.
• Build innovative solutions that improve efficacy, and feed optimisation learnings back into architecture standards so improvements become reusable patterns rather than one-off fixes.
• undefined
• Drive ongoing hydration of the enterprise Agent Catalogue and Skill Registry, making sure reusable agents, skills, tools, prompts, integrations, architecture patterns and accelerators emerging from delivery are identified and catalogued.
• Establish metadata that makes assets discoverable and reusable, including capability, owner, technology, version, dependencies, applicability and lifecycle status.
• Assess new demand against existing assets before a new build is authorised.
• Identify duplicate or overlapping agents and skills across platforms and domains, and recommend consolidation where multiple teams have developed similar capabilities.
• Work with business and technical subject matter experts to keep catalogue content current and usable.
• undefined
• Convert recurring solution requirements into reusable enterprise architecture and engineering patterns.
• Encourage composition of solutions from approved skills and reusable building blocks rather than monolithic agent implementations.
• Partner with engineering teams to industrialise successful proofs of value into repeatable accelerators.
• Track adoption of reusable components, identify barriers to reuse and enable a build once, reuse across products and platforms approach wherever technically appropriate.

REQUIRED QUALIFICATIONS

• Strong solution architecture experience covering artificial intelligence, generative artificial intelligence, automation or modern cloud applications.
• Hands-on experience designing agentic or generative artificial intelligence solutions beyond proof-of-concept stage.
• Understanding of agent orchestration, tool and skill invocation, multi-agent patterns and human-in-the-loop architecture.
• Strong understanding of large language models, context windows, prompting, token consumption and model selection.
• Experience with retrieval-augmented generation, retrieval, grounding, vector search and enterprise knowledge integration.
• Strong application programming interface, integration and event-driven architecture knowledge, and an understanding of emerging standards such as Model Context Protocol (MCP) and reusable tool and skill architectures.
• Cloud architecture experience on Microsoft Azure or Google Cloud Platform.
• Ability to review technical designs for scale, security, resilience, observability and maintainability.
• Strong understanding of artificial intelligence security, privacy, Responsible AI and governance principles, and experience translating governance requirements into technical design controls and architecture patterns.
• Ability to create architecture decision records, technical design documents and reusable reference patterns.
• Practical experience optimising generative artificial intelligence solutions for tokens, latency, model utilisation and runtime cost, including model routing and right-sizing workloads across model classes.
• Ability to identify architectural causes of unnecessary large language model consumption rather than relying only on prompt-level optimisation.
• Experience with reusable component libraries, application programming interface or service catalogues, agent or skill registries, or equivalent enterprise asset management, including asset metadata, taxonomy, ownership, versioning and lifecycle.
• Ability to identify duplication and convert solution-specific components into reusable architecture or engineering patterns.
• Strong stakeholder skills, with the ability to challenge proposed designs constructively, recommend pragmatic alternatives and communicate technical decisions clearly.

PREFERRED QUALIFICATIONS

• Experience with Microsoft Copilot Studio.
• Experience with Model Context Protocol (MCP) servers, application programming interfaces, plugins, connectors and enterprise tool integration.
• Experience with large language model operations (LLMOps), generative artificial intelligence operations and artificial intelligence observability.
• Experience with model evaluation and benchmarking, and with prompt and context engineering.
• Knowledge of artificial intelligence financial operations (FinOps) and cost-management practices.
• Experience with knowledge graphs and semantic search.
• Experience with DevOps and continuous integration and continuous delivery for artificial intelligence applications.
• Exposure to autonomous, self-healing or NoOps-oriented architectures.
• Experience with developer portals, application programming interface catalogues or internal technology marketplaces.
• Experience in fast-moving consumer goods, retail and eCommerce, or global manufacturing organisations.

At Unilever, inclusion is at the heart of everything we do. We welcome applicants from all walks of life and are committed to creating an environment where everyone can thrive/succeed. All applicants will receive fair and respectful consideration, and we actively support the growth and development of every employee.

Unilever is an Equal Opportunity Employer/Protected Veterans/Persons with Disabilities.