1 day ago
Manchester, United Kingdom or London, United KingdomStaff+
Responsibilities
- Define and maintain reference architectures for finance agents, including orchestration, MCP and tool design, memory, retrieval, human handoff, evaluation, rollback, RAG, graph retrieval, context engineering, model gateways, versioning, and graceful degradation.
- Set model selection and routing strategies across proprietary and open-weight models and cloud AI platforms, balancing cost, latency, reliability, quality, safety, data residency, vendor lock-in, and supportability.
- Design control-plane capabilities covering segregation of duties, approval gates, evidence trails, auditability, identity and access controls, policy enforcement, prompt and model traceability, sensitive-data handling, and explainability.
- Own non-functional architecture and technical assurance for scalability, resilience, security, privacy, accessibility, latency, throughput, disaster recovery, and cost efficiency.
- Define LLMOps and AgentOps standards, evaluation suites, red-teaming practices, monitoring, service levels, feedback loops, release management, incident response, and rollback runbooks.
- Define secure integration patterns for ERP and EPM platforms, data and content services, workflow tools, APIs, and event-driven systems.
- Provide technical authority in client pursuits and lead technical responses for CFO and CIO stakeholders from discovery and proof of value through production transition.
- Establish engineering standards and develop team capability through reusable patterns, architecture decision records, design reviews, exception governance, and mentoring.
- Define measurable finance solution outcomes such as quality, automation and exception rates, control effectiveness, user adoption, and cost to serve.
Requirements
- At least 6 years of relevant professional experience.
- Production experience delivering enterprise agentic or LLM systems at scale, including transitioning proof-of-concept solutions into controlled production and resolving reliability, security, or safety incidents.
- Substantial architecture experience with distributed systems, integrations, APIs, event design, cloud platforms, identity, secrets, encryption, deployment, observability, and production operations.
- Hands-on depth in LLM application architecture, including RAG, embeddings, vector or graph retrieval, tool and function calling, structured outputs, orchestration frameworks, and model gateways.
- Experience with LLM evaluation and reliability engineering, including offline and online evaluation, groundedness, task-quality measures, failure-mode analysis, monitoring, and cost or latency optimization.
- Working knowledge of responsible AI and secure AI delivery, including threat modeling, privacy and PII controls, access control, auditability, model risk, GDPR, and EU AI Act considerations.
- Ability to communicate technical trade-offs to senior technical leaders and finance executives and lead technical shaping in pursuits.
- Ability to translate finance-process, control, and audit requirements into executable architecture and engineering acceptance criteria.
- Desirable experience includes enterprise finance, ERP, financial close, controls or audit, EPM, planning, finance transformation, regulated environments, model-risk management, external assurance, semantic or knowledge-graph architectures, GraphRAG, data-product patterns, managed AI services, and relevant cloud, architecture, security, or AI platform certifications.
Tech Stack
Categories
About Accenture
Accenture is a global professional services firm providing management consulting, systems integration and technology, cybersecurity, and business process outsourcing for enterprises and governments. It operates a services-driven model delivering projects and managed services, often with major cloud and software partners, across industries worldwide. Headquartered in Dublin and publicly traded on the NYSE (ACN), it originated as Andersen Consulting and adopted the Accenture name in 2001.