AI Architect

RELX Group; Poltimore; Híbrido; GBP 120.000 - 190.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Flexible working hours

wellbeing initiatives

Parental leave

Descripción de la vacante

LexisNexis Intellectual Property Solutions (LNIP) is seeking a senior AI Architect to serve as the technical authority for Protégé within PatentSight+. You will define and own the AI architecture vision, spanning from agentic layers to data pipelines, ensuring coherence, scalability and compliance with RELX Responsible AI standards.

The role is a senior individual-contributor position; you will partner with Engineering Leads, PMs, and data teams to drive architectural decisions, ADRs, and

Formación

• Senior software/AI architect with production LLM experience.
• Proven delivery of AI-powered systems with end-to-end architecture.
• Strong Python development and enterprise integration skills.

Responsabilidades

• Define and own the AI architecture vision for Protégé in PatentSight+.
• Architect scalable, secure AI systems aligned with RELX standards.
• Lead ADRs, design documentation, and risk assessments for AI platforms.

Conocimientos

LLM architecture

RAG pipelines

Agentic tooling

Python

Security/reliability

Communicating architecture

Herramientas

Vector databases

Databricks

Elasticsearch

MCP

Descripción del empleo

As an AI Architect, you will be the technical authority for the AI systems that power Protégé within PatentSight+. You will work across the full stack, from the agentic layer down, ensuring every layer is coherent, scalable, secure, and aligned with RELX Responsible AI standards.
This is a senior individual-contributor role with broad influence. You will partner closely with Engineering Leads, Product Managers, Data Scientists, and data teams within LNIP., Define and own the AI architecture vision for Protégé in PatentSight+, ensuring technical decisions are coherent, future-proof, and aligned with product strategy.
Evaluate and recommend AI technologies, modelling approaches, and platform components.
Stay up to date with advances in agentic AI and domain-specific AI research. Translate emerging capabilities into practical architectural recommendations.
Author and maintain Architecture Decision Records (ADRs) and system design documentation, providing a clear and durable record of technical choices and their rationale.
Architect the agentic reasoning systems that enable Protégé to decompose complex patent questions, plan multi-step analyses, and compose insights from multiple data sources.
Design retrieval and search architectures that deliver accurate, low-latency patent intelligence across both structured analytics and unstructured text corpora.
Define patterns for AI-driven enrichment and classification of patent data at scale, ensuring results are dependable, auditable, and consistent with established IP metrics.
Establish prompt engineering standards, evaluation harnesses, and quality frameworks to govern LLM behaviour and maintain output accuracy in production.
Partner with Product Management to assess technical feasibility and shape the AI roadmap, translating product goals into deliverable system designs.
Collaborate with Security and Platform teams to ensure AI systems meet enterprise requirements for access control, data privacy, and regulatory compliance.
Ensure all AI systems comply with RELX Responsible AI Principles.
Lead AI risk assessment activities, contributing to compliance with applicable regulatory frameworks.
Communicate complex architectural decisions clearly to senior leadership, engineering teams, and non-technical stakeholders.

Essential

• Strong professional software engineering expertise, with experience in a dedicated AI/ML architecture, principal engineer, or distinguished engineer role.
• Proven track record delivering production LLM-based systems, including RAG pipelines, agentic/tool-use frameworks, and multi-step reasoning workflows.
• Strong proficiency in Python for AI service development; working knowledge of C# or equivalent compiled language for enterprise microservice integration.
• Hands-on experience with vector databases and semantic search pipeline design.
• Experience with Model Context Protocol (MCP).
• Experience with large-scale data platforms such as Databricks and search engines such as Elasticsearch, in an analytical or AI feature engineering context.
• Demonstrated ability to design enterprise-grade AI systems with strong non-functional requirements: security, privacy, reliability, cost governance, and observability.
• Experience communicating complex architectural decisions through written documents, diagrams, and presentations to diverse audiences.

Desirable

• Background in the intellectual property, legal technology, or scientific information domain; familiarity with patent data structures and classification systems.
• Knowledge of Responsible AI Principles.
• Advanced degree in Computer Science, Artificial Intelligence, Data Science, or a related field.
• Experience designing event-driven, cloud-native architectures using Kafka (or equivalent streaming platforms), including topic design, schema governance, and consumer patterns.

Excited to uncover insights from complex data and turn them into impactful business decisions?
Do you enjoy building predictive models, experimenting with advanced analytics, and solving real-world challenges with data?

About the team

LexisNexis Intellectual Property Solutions (LNIP) is the global leader in patent intelligence, bringing clarity to innovation for businesses, law firms, universities, and government agencies worldwide. Our mission is to help the innovation community make better decisions faster, with greater confidence, combining the world's most trusted patent data with sophisticated analytics, AI-powered insights, and purpose-built workflows.
Protégé in PatentSight is LNIP's next-generation agentic AI assistant, purpose-built for strategic patent analysis. Protégé replaces complex filter-based workflows with natural language questions, surfacing structured, decision-ready insights grounded in trusted data and established metrics.

We promote a healthy work/life balance across the organization. We offer an appealing working prospect for our people. With numerous wellbeing initiatives, shared parental leave, study assistance and sabbaticals, we will help you meet your immediate responsibilities and your long-term goals.

Working flexible hours - flexing the times when you work in the day to help you fit everything in and work when you are the most productive.

Working for you

We know that your well-being and happiness are key to a long and successful career. These are some of the benefits we are delighted to offer:

• Generous holiday allowance with the option to buy additional days.
• Health screening, eye care vouchers, and private medical benefits
• Wellbeing programs
• Life assurance
• Access to a competitive contributory pension scheme
• Save As You Earn share option scheme.
• Travel Season ticket loan.
• Electric Vehicle Scheme
• Optional Dental Insurance
• Maternity, paternity, and shared parental leave
• Employee Assistance Programme
• Access to emergency care for both the elderly and children
• RECARES days, giving you time to support the charities and causes that matter to you.
• Access to employee resource groups with dedicated time to volunteer.
• Access to extensive learning and development resources
• Access to employee discounts scheme via Perks at Work

About the Business

At LexisNexis Intellectual Property (LNIP), we believe that whenever a person works on a patent and understands the future trajectory of a specific technology, that person has the potential to fundamentally change how society operates. We are proud to directly support and serve these innovators in their endeavors to better humankind. We enable innovators to accomplish more by helping them make informed decisions, be more productive, comply with regulations, and ultimately achieve superior results. By harnessing the latest advances in machine learning combined with expert analysis, LexisNexis Intellectual Property is disrupting how actionable insight is extracted from patent data. Information can now be accessed with efficiency, accuracy and at a speed that is just not possible by traditional methods. Our overall success is measured by how well we deliver these results.