Artificial Intelligence Engineer

Lorien; Manchester; Hybrid; GBP 100,000 - 110,000; Full time

Job summary

Lorien is seeking a Senior Software Engineer in Manchester for a hybrid role combining hands-on software development with AI tooling in a digital betting and gaming environment.

You will design and implement production systems, with LLM APIs and agent workflows, while measuring results with evidence-based methods and collaborating with a large engineering organization.

Qualifications

• Hands-on software engineering experience in production systems.
• Experience building with LLMs and agent-based workflows.
• Strong testing, CI/CD, and code review practices.
• Experience with Git platforms and observability tools.

Responsibilities

• Build and operate production software with AI tooling.
• Create tooling and workflows for real codebases.
• Evaluate AI outputs with evidence-based methods.
• Collaborate with engineers to drive adoption.

Skills

Production software

CI/CD

Code review

LLM APIs

Agent workflows

Python

SQL

Testing

Observability

Tools

Git platforms

Docker

Kubernetes

AWS

FastAPI

Jenkins/Harness

Bitbucket

Job description

Manchester (hybrid, 2 days a week in the office) | Permanent | £100,000-£110,000 + bonus

A leading digital and retail business in the global betting and gaming industry is looking for an engineer who’d rather prove what works than sell what’s fashionable.

With around 250 engineers building and running its platforms, the business wants to use LLMs and coding agents to help them deliver better software, faster, and to be able to show the evidence. This is a hands-on role. You’ll work out where AI helps engineers and where it doesn’t, build the tooling and workflows that make it work in real codebases, and measure the results honestly. You’ll use the best available models, coding agents and open-source tools. This isn’t a model-building or research role.

What they’re looking for:

• Strong professional software engineering experience, including building and operating production software
• Excellent programming and software design skills, with a solid grasp of testing, CI/CD and code review
• Hands-on experience building with LLM APIs, including tool calling and agentic workflows
• Day-to-day use of AI coding tools and agents on real codebases, with an evidence-based view of where they help and where they hurt
• A practical understanding of how LLMs and agents fail: plausible but wrong code, fixes that mask symptoms, tests gamed to pass, context limits and cost growth
• Experience integrating with Git platforms, CI/CD, issue trackers and observability tooling
• Experience designing evaluations for AI outputs, or comparable experimental rigour
• Python (or similar) and SQL for preparing code, documents and tickets for retrieval
• Credibility with engineers and the ability to influence without line authority, including winning over sceptics
• Helpful: Bitbucket, Jenkins/Harness, Docker, Kubernetes, AWS, FastAPI, MCP, DORA-style measurement, RAG and vector search, self-hosted open-weight models, or a regulated environment such as gambling or financial services