AI/LLM Systems Architect (Agentic & RAG)

Accenture PLC; Greater London; On-site; GBP 90,000 - 140,000; Full time

Job summary

Accenture PLC in London seeks an AI Large Language Model (LLM) Technology Architect to lead hands-on design and delivery of enterprise AI systems, owning architecture decisions, building agent orchestration, and integrating foundation models with enterprise data.

The role spans AI/ML, RAG, memory systems, and governance, focusing on scalable, secure solutions and architecture artifacts for cross-functional teams.

Qualifications

• Proven experience in designing & deploying enterprise grade advanced AI solutions using agentic, generative and classical AI/ML with a cloud vendor.
• Practical experience in the Agentic, LLM and Generative AI space.
• Well versed in coding using Python.
• Solid foundation in architecting and operationalizing LLM driven application architecture patterns.
• Professional working experience in coding, ML, DL and NLP solutions and applications.
• Several years of hands on experience as a machine learning architect in the industry designing big data, ML, large scale analytical engineering solutions.

Responsibilities

• Independently design, build, and deliver software components across the AI architecture — owning them end to end from design through implementation, integration, and testing as a hands-on practitioner
• Design and build AI agent architectures — including individual agents, their prompts, tools, and skills, multi-agent orchestration, and memory systems — making deliberate design pattern and technology choices
• Design and implement agent orchestration patterns that handle task handoffs, communication, state management, and error recovery, validating them through hands-on prototyping
• Evaluate multiple design options and technical approaches, making deliberate, justified design choices that balance capability, cost efficiency, performance, and enterprise-grade reliability
• Design, build, and run evaluation strategies and harnesses that measure agent and system quality on metrics such as accuracy, relevance, and faithfulness, translating findings into design improvements
• Architect and implement foundation model integrations — selecting the right models, invocation patterns, and customization approaches (finetuning, RAG, custom integration) based on capability, cost, and performance trade-offs
• Design and build model adaptation and fine-tuning pipelines, applying working knowledge of transformer-based architectures to inform model selection and optimization
• Design and build the AI context layer — including context graph design and ingestion pipelines that parse, chunk, enrich, and index structured and unstructured enterprise content, and the retrieval components that ground AI outputs in the client's knowledge
• Build embedding, vector storage, and retrieval (semantic, hybrid, reranking) into end-to-end RAG pipelines, applying integration patterns that connect to enterprise data sources
• Design and implement context assembly and memory components that manage prompts, context windows, and conversational state for grounded, accurate outputs
• Identify, design, and build reusable components and solution patterns that accelerate delivery and can be templated across engagements
• Design for cost efficiency and performance — optimizing model usage, inference patterns, caching, and resource utilization to meet target latency, throughput, and cost objectives
• Design, build, and validate systems against enterprise non-functional requirements — implementing guardrails, prompt-injection defenses, PII handling, and access controls for security and Responsible AI
• Build governance controls including versioning, audit logging, and lineage tracking, and produce the model documentation that keeps systems auditable
• Build observability into systems — logging, tracing, monitoring, alerting, and cost tracking — to ensure AI solutions remain healthy, performant, and scalable in production
• Produce detailed architecture artifacts — including ADRs, architecture blueprints, design documents, agent orchestration and integration pattern specifications, component and data flow diagrams
• Continuously learn, evaluate, and apply new design patterns, frameworks, and technologies across the fast-evolving AI landscape
• Collaborate with cross-functional delivery teams — data engineers, ML engineers, and application developers — to translate requirements into concrete architecture decisions that meet stakeholder needs

Skills

AI architecture

Python

LLM & Generative AI

Cloud experience

NLP solutions

Machine learning

Education

Bachelor's Degree or equivalent

Tools

AWS

Azure

GCP

Job description

Accenture PLC in London seeks an AI Large Language Model (LLM) Technology Architect to lead hands-on design and delivery of enterprise AI systems, owning architecture decisions, building agent orchestration, and integrating foundation models with enterprise data.

The role spans AI/ML, RAG, memory systems, and governance, focusing on scalable, secure solutions and architecture artifacts for cross-functional teams.