Senior AI Software Engineer

## Senior AI Software Engineer Apply:
Windsor:
Full time:
Posted Today:
End Date:
October 3, 2026 (16 days left to apply):
R0083247
** Join us, be part of more.
** We’re so much more than an energy company. We’re a family of brands revolutionising how we power the planet. We're energisers. One team of 21,000 colleagues that's energising a greener, fairer future by creating an energy system that doesn’t rely on fossil fuels, whilst living our powerful commitment to igniting positive change in our communities. Here, you can find more purpose, more passion, and more potential.

That’s why working here is #MoreThanACareer. We do energy differently - we do it all. We make it, store it, move it, sell it, and mend it.
** An opportunity to play your part**. You will join the Channel Platforms team, which owns Centrica’s customer conversation estate across voice, chat and email. Our agents are already live: a pay as you go voice assistant built on a real time speech to speech model, a multi channel customer facing agent spanning voice, chat and Whats App, and a standalone agentic webchat service running on Agent Core Runtime.

As a Senior AI Engineer you will own the intelligence layer of these products. That means the agent’s reasoning and orchestration, the tools it can call, the knowledge it retrieves, the guardrails that constrain it, and the evaluation that proves it works. You will decide what good looks like and then build the measurement to show whether we are hitting it.

This is a role for someone who has taken generative AI past the demo stage. Our problems are the hard ones that show up after launch: grounding answers in the right source, keeping voice latency low enough to feel natural, handing off to a human at the right moment, and proving to a governance board that the system behaves safely  do not need a contact centre background.

If you are a strong engineer who has built real agentic systems on Bedrock or a comparable platform, we will teach you the domain.
** Location**: UK-based hybrid role, occasional travel to site.
** The Day to day
*** Design and build agentic services on Amazon Bedrock and Agent Core Runtime, including multi step orchestration, state and memory management, and graceful handling of failure and ambiguity.
* Build and own the tool layer that agents act through, exposing business capability such as account lookup, billing and identity as reliable, well described actions with sensible error semantics.
* Build retrieval augmented generation over Bedrock Knowledge Bases, taking ownership of content preparation, chunking, embedding strategy, retrieval quality and answer grounding.
* Treat prompts as engineering artefacts. Version them, test them, and understand precisely what changed when behaviour shifts.
* Build the evaluation harness. Define what accuracy, containment and safe behaviour mean for each product, assemble regression sets, and make it possible to ship a prompt or model change with evidence rather than optimism.
* Implement guardrails and safety controls, including PII handling, out of scope refusal, jailbreak resistance and clean escalation to a human advisor.
* Engineer for latency and cost. Streaming, model selection and routing, caching and token budgets all matter, and in voice they matter in real time where a pause of a few hundred milliseconds is felt by the customer.
* Instrument agent behaviour end to end so that tool failures, retrieval misses and abandoned conversations are visible in Datadog and Quick Sight, not discovered through complaints.
* Support live AI services in production, investigating incidents and diagnosing non deterministic behaviour, then closing the loop with permanent fixes.
* Make and document build versus buy calls, writing…