Senior Production AI Agentic Systems Engineer

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

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.