About this role
Salary: £61,000 - 101,000 per year
Requirements: Extensive software engineering experience in production environmentsHands-on experience designing and deploying agentic AI solutions in a production environmentDemonstrated experience with agentic orchestration frameworks such as LangGraph, CrewAI, AutoGen, or equivalent at production depthDirect experience calling LLM APIs such as OpenAI, Anthropic, or Vertex AI in production code, including provider abstraction, token management, latency, and cost tradeoffsRAG pipeline ownership, including embeddings, chunking strategy, vector databases, and context engineeringLLMOps fundamentals, including eval harness design, prompt versioning, and production observabilityCloud-native engineering maturity with Kubernetes, Docker, microservices, serverless, CI/CD, and IaC such as Terraform or HelmStrong Python skills; Java or an equivalent backend language is acceptableProduction debugging and observability experiencePeople leadership experience, including managing, developing, and performance-managing a team of engineers, setting individual development plans, and conducting career conversations Responsibilities: Architect and govern production-grade agentic systems at enterprise scale, including multi-agent orchestration, RAG pipelines, policy-based routing, memory management, and programme-level lifecycle observabilityDefine RAG pipeline standards across engagements, including chunking and embedding strategies, quality benchmarks, and metric-backed tradeoff decisionsSet multi-LLM integration standards with vendor-agnostic architecture, fallback routing, and cost governance across providersOwn LLMOps at programme scale, including eval strategy, prompt governance, observability tooling standards, safety monitoring, and cost controls across multiple concurrent systemsLead client engineering engagements at a senior level, facilitate architecture design sessions, lead proof-of-concept delivery, and align client technology leadership with delivery teamsShape and publish reusable patterns, accelerators, and engineering standards that scale across the practice and reduce ramp-up time on new client engagementsOwn the measurement framework for agentic system quality by defining accuracy, latency, safety, and cost metrics and presenting programme-level AI impact in business terms to senior client stakeholders Technologies: Agentic AIAIArchitectBackendCI/CDCloudDockerHelmJavaKubernetesLLMPythonRAGServerlessTerraformmicroservices More:
We are partnering directly with Accenture to hire for this role. We build production-grade agentic AI systems for enterprise environments, working directly with client engineering teams and across the full enterprise technology stack. We offer breadth across industries and enterprise complexity, along with vendor fellowship access inside Anthropic, OpenAI, Microsoft, and Google engineering teams and a direct pathway to the Forward Deployed Engineer programme. Accenture is a leading global professional services company serving clients in more than 120 countries, with technology at the core of its work and strong capabilities across cloud, data, AI, and global delivery. We are a talent- and innovation-led company committed to creating 360 value for our clients, each other, our shareholders, partners, and communities.
last updated 37 week of 2026