Applied AI Engineer – Prompting & Evaluation

Salary: £58,000 - 98,000 per year

Requirements:

• We need solid production experience with C# .NET, including working safely in established codebases you did not write.
• We need hands-on experience building with large language models, including prompt design, context engineering and structured outputs.
• We need a track record of shipping quickly, with examples of taking work from idea to working software in weeks rather than quarters.
• We need experience testing or evaluating LLM outputs in a structured way and using the results to improve quality.
• We need daily fluency with AI coding tools such as GitHub Copilot, Cursor or equivalents.
• Desirable: experience with retrieval-augmented generation, agentic workflows, tool use, vector search or embeddings in production.
• Desirable: experience with LLM APIs across more than one provider and an understanding of their trade-offs.
• Desirable: exposure to distributive trades, rental, retail, automotive aftermarket parts or garage management.
• Desirable: experience modernising or extending long-lived systems, in .NET or elsewhere.
• Desirable: familiarity with evaluation frameworks, test datasets or automated quality pipelines for AI outputs.

Responsibilities:

• We build AI features quickly and properly, from prompt and context design through to full LLM integration in established C# .NET codebases.
• We make features production-grade with error handling, fallbacks, latency management, logging, monitoring and solid evaluation before anything reaches a customer.
• We stay sharp, keep up with a fast-moving space and share knowledge through code, examples and conversation.
• We design and build prompts, context strategies and LLM integrations for product features where accuracy matters.
• We work primarily in C# .NET, integrating AI capability into established codebases through clean service boundaries and sensible abstractions.
• We prototype in days, harden in weeks, and move fast on real deadlines.
• We build evaluation alongside the feature, test against real business cases and measure quality honestly.
• We handle the unglamorous parts well, including error handling, fallbacks, latency, token cost, logging and monitoring.
• We work with the engineers who own each codebase, fitting into their patterns and pipelines so the work is maintainable.
• We keep up as models, tools and providers change, and choose pragmatically on quality, cost and latency.
• We work with product managers, product owners and subject matter experts to understand the business problem properly.
• We leave documentation in better shape than we found it and contribute to shared knowledge and engineering standards as the teams AI practice matures.

Technologies:

• AI
• C#
• Copilot
• Cursor
• ERP
• GitHub
• Support
• LLM
• ASP.NET
• LESS
• RAG

More:

We are Klipboard, formerly Kerridge Commercial Systems (KCS), a global and growing business providing specialist software, services and support for distributive trade customers around the world. Our ERP and SaaS solutions help wholesalers, distributors, merchants and retailers source effectively, stock efficiently, sell profitably and service competitively. We have offices in the UK, Ireland, The Netherlands, South Africa, Kenya and North America. We offer a flexible hybrid work policy with three days in the office and two days working from home, supporting collaboration and remote convenience. We are embracing AI and emerging technologies across our products and ways of working, and we value curiosity, openness to change and continuous learning. We are committed to diversity, equity and inclusion, and we encourage applicants even if they do not meet every requirement.

last updated 33 week of 2026