1 day ago
London, United KingdomMid Level
Responsibilities
- Build and deploy agentic workflows for finance processes including reconciliations, journals, exception handling, disputes, collections, and variance explanation.
- Implement LLM application patterns including tool and function calling, structured outputs, retrieval, context and memory management, multi-agent orchestration, and prompt or configuration versioning.
- Integrate with ERP, EPM, document, and workflow systems using secure APIs, events, identity controls, data transformation, and reusable connectors.
- Create evaluations, automated tests, observability, red-team scenarios, and quality, groundedness, latency, and cost measures for agent behavior.
- Build finance-user interfaces for reviewing, approving, overriding, and evidencing agent actions, including provenance, citations, accessibility, and error recovery.
- Package and operate solutions with cloud AI services, containers or serverless components, infrastructure as code, secrets and configuration management, monitoring, release controls, and rollback.
- Collaborate directly with finance users, process specialists, architects, and data engineers to clarify requirements, demonstrate increments, and document operating procedures and runbooks.
- Contribute tested code, evaluation assets, reference implementations, reusable patterns, and implementation guidance to the practice asset base.
Requirements
- At least four years of relevant professional experience.
- Strong software engineering discipline with Python and at least one additional production language such as TypeScript or equivalent, plus version control, testing, CI, maintainable code, SQL, API design, code review, and secure coding practices.
- Hands-on LLM application development involving tool use, structured outputs, retrieval, agent frameworks, embeddings, vector or graph retrieval, prompt and configuration management, and enterprise integrations.
- Practical experience with evaluation, observability, LLMOps or AgentOps, versioning, monitoring, release and rollback, and analysis of quality, latency, and cost.
- Understanding of secure enterprise integration and sensitive-data handling, including authentication, authorization, secrets, logging, and PII-aware design.
- Ability to work client-side with non-technical finance users and translate their needs into testable requirements while explaining options, risks, and trade-offs.
- Front-end capability with technologies such as React, Next.js, or an equivalent framework is desirable.
- Exposure to SAP, Oracle, Workday, Anaplan, OneStream, finance processes, MCP, graph or semantic retrieval, data engineering, event-driven integration, or workflow orchestration is desirable.
- Experience deploying software or data products on Azure, AWS, GCP, Databricks, Snowflake, or Palantir using containers, Kubernetes, or serverless patterns is desirable.
- Experience in regulated environments or under responsible-AI, security, or model-risk controls is desirable.
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.