Senior AI Engineer: Agentic Systems & GenAI Orchestration

Centrica plc; Clewer Village; On-site; GBP 85,000 - 120,000; Full time

Benefits offered by this job

Hybrid work model

Job summary

Centrica plc is seeking a Senior AI Engineer to own the intelligence layer of our agentic products, building reliable, scalable AI services for customer interactions across voice, chat and email. You will design and implement multi-step orchestration, retrieval-augmented generation, and governance controls, with a strong emphasis on performance, safety and measurable outcomes.

Based in the UK with hybrid work and occasional travel to sites, you will collaborate with product owners, governance

Qualifications

• Substantial software engineering experience with strong Python.
• Production delivery of LLM/agentic systems for real users and the ability to discuss trade-offs.
• Hands-on experience with tool and function calling, multi-step agent orchestration and managing conversational state across turns.
• Experience deploying AI services with retrieval-augmented generation and evaluation grounding.
• Experience deploying and operating AI services in cloud environments using serverless or container-based architectures, IaC (Terraform) and CI/CD.
• Practical application of responsible AI including data privacy, guardrails and governance.

Responsibilities

• Design and build agentic services on Bedrock and AgentCore Runtime, including multi-step orchestration, state and memory management, and graceful handling of failure and ambiguity.
• Build the tool layer that agents act through, exposing business capabilities with reliable error semantics.
• Implement retrieval-augmented generation with quality evaluation and grounding of answers.
• Treat prompts as engineering artefacts: version, test and track changes to behaviour.
• Define evaluation criteria (accuracy, containment, safety) and build regression sets for releases.
• Implement guardrails and safety controls, including PII handling and escalation to humans where needed.
• Instrument agent behavior end-to-end and monitor with Datadog/QuickSight; plan build-vs-buy decisions and architecture governance.

Skills

Python

LLM systems

Agent orchestration

Evaluation harness design

Cloud deployment

Terraform

CI/CD

Responsible AI

Communication

Education

Bachelor's degree in Computer Science or related discipline

Tools

Amazon Bedrock

AgentCore Runtime

Bedrock Knowledge Bases

Bedrock Guardrails

AWS Certification

Job description

Centrica plc is seeking a Senior AI Engineer to own the intelligence layer of our agentic products, building reliable, scalable AI services for customer interactions across voice, chat and email. You will design and implement multi-step orchestration, retrieval-augmented generation, and governance controls, with a strong emphasis on performance, safety and measurable outcomes.

Based in the UK with hybrid work and occasional travel to sites, you will collaborate with product owners, governance