Artificial Intelligence Engineer

Apache Associates; Hungerford; On-site; GBP 70,000 - 100,000; Full time

Job summary

Apache Associates is seeking a Senior Software Engineer to lead production AI features across the R&D landscape. You will design prompts, context strategies and agentic workflows to deliver real-world AI capabilities.

You will coach engineers, establish internal AI practices, and work with multiple LLM providers to ensure robust, scalable solutions while balancing quality and cost. This is a senior, hands-on role in a rapidly evolving AI-driven engineering environment.

Qualifications

• Several years of production software experience in C#.Net and React Front-end technologies.
• Hands-on experience with Large Language Models in commercial environments.
• Experience building evaluation frameworks and test harnesses for LLM outputs.
• Evidence of mentoring and coaching other engineers.

Responsibilities

• Design, build and refine prompts, context strategies and agentic workflows for real-world AI features.
• Develop robust approaches to evaluating LLM outputs using measurable quality standards.
• Work with multiple LLM providers and models, balancing quality, cost and latency.
• Collaborate with Product Managers and subject matter experts to define problems and design AI solutions.
• Coach engineers across teams to extract more value from LLMs and AI coding tools.
• Run pairing sessions, technical reviews, workshops and one-to-one coaching.
• Create reusable prompt patterns, templates, evaluation harnesses and internal guidance.
• Lead internal AI communities of practice and establish prompting/evaluation standards.
• Define what good prompting and evaluation looks like across R&D and keep it updated.
• Provide leadership with measurable evidence of AI value and challenge unduly impressive demos.
• Promote high standards around accuracy, safety and data handling.
• Help teams adopt AI tooling in legacy codebases without stalling greenfield work.
• Represent the organisation externally through talks, articles or open-source work.

Skills

C#.Net

React Front-end

LLMs

Prompt engineering

Evaluation frameworks

Mentoring

GitHub Copilot

Tools

LangChain

Semantic Kernel

Job description

Apache Associates are working with an ambitious SaaS organisation that is investing heavily in AI across its products and engineering function. We’re looking for a Senior Software Engineer to take a leading role in turning AI capabilities into genuinely useful, production-ready solutions.

This is a senior, hands‑on position for someone who is as passionate about building with AI as they are about helping other engineers get better at it.

You’ll be responsible for designing and refining prompts, context strategies and agentic workflows, while also establishing best practice around evaluation and AI-assisted development across a large engineering organisation.

The Role

This isn't simply an AI engineering role focused on building individual features. You'll become a key technical voice for how AI is used across the wider R&D organisation.

You'll work closely with engineers, architects, product teams and subject matter experts, helping teams understand where AI can genuinely add value and, equally importantly, where it shouldn't be used.

A major part of the role will be raising the capability of other engineers through coaching, pairing, workshops, knowledge-sharing and reusable tools and resources.

You'll also establish standards around prompt engineering, context engineering and evaluation, ensuring the organisation remains rigorous as models, tools and techniques evolve.

What You'll Be Doing

• Design, build and refine prompts, context strategies and agentic workflows for real-world AI product features.
• Develop robust approaches to evaluating LLM outputs, using real business cases and measurable quality standards.
• Work across multiple LLM providers and models, making pragmatic decisions around quality, cost and latency.
• Work closely with Product Managers, Product Owners and subject matter experts to understand the underlying business problem before designing the AI solution.
• Coach and mentor engineers across multiple teams, helping them get significantly more value from LLMs and AI coding tools.
• Run pairing sessions, technical reviews, workshops and one-to‑one coaching.
• Build and maintain reusable prompt patterns, templates, evaluation harnesses and internal guidance.
• Establish and lead an internal AI community of practice where engineers can share successes, failures and lessons learned.
• Define what "good" looks like for prompting, context engineering and evaluation across R&D.
• Keep those standards current as models, providers and AI tooling evolve.
• Provide engineering leadership with measurable evidence of where AI is delivering genuine value.
• Act as a constructive challenger when an AI solution looks impressive in a demo but isn't robust enough for production.
• Promote high standards around accuracy, safety and data handling.
• Help engineers working within established and legacy codebases adopt AI tooling effectively, rather than focusing solely on greenfield development.
• Potentially represent the organisation externally through talks, articles or open‑source contributions.

What We're Looking For

This role requires someone who is an engineer first, with substantial practical experience applying AI in real‑world software environments.

We're particularly interested in people who can demonstrate:

• Several years of experience building and shipping production software in C#.Net and react Front‑end technologies.
• Significant hands‑on experience working with Large Language Models in commercial environments.
• Strong experience with prompt engineering, context engineering and structured outputs.
• Experience building evaluation frameworks, test harnesses or datasets for LLM outputs.
• Evidence of using evaluation and data to measurably improve AI quality.
• A proven ability to mentor, coach and develop other engineers.
• Experience delivering internal training, workshops, communities of practice or similar knowledge‑sharing initiatives.
• Daily experience with AI development tools such as GitHub Copilot, Cursor or equivalent.
• A pragmatic understanding of both the strengths and limitations of AI coding tools.
• The confidence to challenge assumptions and use evidence rather than hype to determine whether an AI approach is actually working.

It would be advantageous if you have experience with:

• RAG (Retrieval‑Augmented Generation)
• Agentic workflows and tool use
• Vector search and embeddings
• LLM orchestration frameworks such as LangChain, Semantic Kernel or equivalents
• Multiple LLM providers and an understanding of their respective strengths and weaknesses
• Automated test suites and evaluation datasets for AI outputs
• AI adoption within established or legacy codebases
• Distributive trades, rental, retail, automotive aftermarket or garage management
• Public speaking, technical writing or open‑source contributions

Why This Role?

This is a genuinely influential opportunity within an organisation that is embracing AI at pace.

You'll have the opportunity to influence not just what AI features get built, but how an entire engineering organisation approaches AI.

You'll be working across multiple engineering teams, helping establish reusable practices and standards rather than solving the same problems repeatedly.

The successful candidate will be someone who enjoys seeing other engineers improve because of their coaching and guidance, and who gets as much satisfaction from spreading good practice as they do from solving the original technical problem.

The Person

You'll be curious, pragmatic and technically rigorous, but also someone who genuinely enjoys helping others.

You're comfortable working with engineers at very different levels of AI experience – from enthusiastic early adopters to people who remain sceptical about the technology.

You won't be someone who believes AI is the answer to everything. Instead, you'll be interested in understanding where it genuinely creates value, proving that through evidence and helping others apply it effectively.

If you're an experienced software engineer who has moved beyond experimenting with AI and is now building with LLMs in the real world – while helping other engineers do the same – we’d love to hear from you.