AI Native SW Engineering Specialist / Sr Consultant

Accenture UK & Ireland; Greater London; Hybrid; GBP 120,000 - 180,000; Full time

Job summary

Accenture UK & Ireland seeks a senior AI engineer to design and deploy production-grade agentic systems in client environments. You will own end-to-end RAG pipelines, embeddings, vector databases, and context engineering, coordinating across multiple LLM providers with a focus on reliability and cost efficiency.

You will embed with client engineering teams, develop reusable patterns and playbooks, and define metrics on accuracy, latency, and safety to drive business value.

Qualifications

• Hands-on experience shipping production-grade agentic AI systems.
• Comfort designing and deploying end-to-end RAG pipelines.
• Experience integrating multiple LLM providers in production.
• Strong backend engineering and observability capabilities.

Responsibilities

• Design and build production-grade agentic systems end-to-end: multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and lifecycle observability
• Build and own RAG pipelines: embeddings, chunking strategy, vector search, context window engineering and tuning against real quality targets
• Integrate and abstract across multiple LLM providers - OpenAI, Anthropic, Vertex AI, and open-source models
• Implement LLMOps in production: eval harnesses with real quality metrics, prompt versioning, observability tooling
• Embed directly with client engineering teams to design, prototype, and deploy agentic solutions
• Define and use metrics to measure agent accuracy, latency, safety, and cost-effectiveness

Skills

Python

Kubernetes

Docker

LLMOps

RAG pipelines

LLM APIs

Vector databases

Observability

CI/CD

Terraform

Helm

Java

Production debugging

Agentic systems

Cloud

Tools

LangSmith

Braintrust

Job description

You build the systems that actually make AI work in enterprise environments, not demos, not prototypes that stall after a pilot, but production agentic architectures running inside real client organizations. The difference between an AI Engineer and what we are looking for is straightforward: you have shipped a multi-agent system in production, you have owned the eval harness, and you know what happens when your agent fails at 2am because you have lived it.

Key Responsibilities

• Design and build production-grade agentic systems end-to-end: multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and lifecycle observability
• Build and own RAG pipelines: embeddings, chunking strategy, vector search, context window engineering and tuning against real quality targets
• Integrate and abstract across multiple LLM providers - OpenAI, Anthropic, Vertex AI, and open-source models - with fallback routing, token, cost, and latency management
• Implement LLMOps in production: eval harnesses with real quality metrics, prompt versioning, observability tooling (LangSmith, Braintrust, or equivalent), cost and safety monitoring
• Embed directly with client engineering teams to design, prototype, and deploy agentic solutions - workshops, proofs of concept, code-with sessions, and architecture walkthroughs
• Build reusable patterns, accelerators, and playbooks that scale beyond the individual client engagement and enable the next one to start faster
• Define and use metrics to measure agent accuracy, latency, safety, and cost-effectiveness; present findings and recommendations to client stakeholders in business terms
• Extensive software engineering experience in production environments
• Hands-on experience designing and deploying agentic AI solutions in a production environment - non-negotiable
• Demonstrated experience with agentic orchestration frameworks: LangGraph, CrewAI, AutoGen, or equivalent - at production depth, not tutorial level
• Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code: provider abstraction, token management, latency and cost tradeoffs
• RAG pipeline ownership: embeddings, chunking strategy, vector databases, and context engineering
• LLMOps fundamentals: eval harness design, prompt versioning, and production observability
• Cloud-native engineering maturity: Kubernetes, Docker, microservices, serverless, CI/CD, and IaC (Terraform or Helm)
• Strong Python; Java or equivalent backend language acceptable; production debugging and observability experience
• Quality of experience is weighted over years, a candidate who has shipped three production agentic systems in four years is preferred over a generalist with passive AI exposure