AI Engineer

• C# .NET (primary development language)
• Large language model APIs across multiple providers
• AI coding tools: GitHub Copilot, Cursor or equivalents
• Prompt engineering and context design patterns
• Retrieval-augmented generation (RAG), vector search, embeddings (desirable)
• Evaluation frameworks and automated quality pipelines for AI outputs

Technical and Professional Expertise

• Solid production experience with C# .NET, including working in established codebases you did not write, and shipping changes into them safely.
• Hands-on experience building with large language models: prompt design, context engineering and structured outputs, in real work rather than tutorials.
• A track record of shipping quickly, with examples of taking something from idea to working software in weeks rather than quarters.
• Experience testing or evaluating LLM outputs in some structured way, and using the results to improve quality., * Solid production experience with C# .NET, including working in established codebases you did not write, and shipping changes into them safely.
• Hands-on experience building with large language models: prompt design, context engineering and structured outputs, in real work rather than tutorials.
• A track record of shipping quickly, with examples of taking something from idea to working software in weeks rather than quarters.
• Experience testing or evaluating LLM outputs in some structured way, and using the results to improve quality.
• Daily fluency with AI coding tools such as GitHub Copilot, Cursor or equivalents., * AI & Data Science Job Titles
• C Programming (Software)
• Copilot Mentions
• LLM Development & Deployment

"At Klipboard we've introduced a flexible hybrid work policy, where employees spend three days in the office and two days working from home. This approach promotes a balanced work environment that combines office collaboration with the comfort and convenience of remote work." Klipboard provides specialist software, services and support to deliver fully integrated trading and business management solutions to companies in the distributive trade - wherever they are in the world. With a unique depth of knowledge and experience in ERP/SaaS solutions, Klipboard has a wide range of clients includes wholesalers, distributors, merchants and retailers from small traders to multinational enterprises. Klipboard has offices in the UK, Ireland, The Netherlands, South Africa, Kenya and North America. Our mission is simple: to design and deliver high performance, integrated ERP solutions that enable our distributive trade customers to source effectively, stock efficiently, sell profitably and service competitively. A hands-on building role: taking AI features from idea to shipped, working software quickly, inside real products that real businesses depend on. You design prompts, manage context, integrate models, build evaluations and handle the plumbing and the polish - all of it. Crucially, most of this work happens in established C# .NET codebases, not greenfield projects. Klipboard's products have been earning their keep for years, and the job is landing modern AI capability inside them cleanly, without breaking what already works. Fast matters here, but fast with evidence - every AI feature needs evaluation behind it before customers see it. We would rather you shipped something measured and honest this sprint than something perfect next quarter. Key Activities and Contributions * Design and build prompts, context strategies and LLM integrations for product features, in domains where a confidently wrong price, part match or stock answer is worse than no answer. * Work primarily in C# .NET, integrating AI capability into established codebases through clean service boundaries, sensible abstractions and respect for the code that is already there. * Move fast on real deadlines - prototype in days, harden in weeks, and know the difference between a corner that can be cut and one that cannot. * Build evaluation alongside the feature, not after it - test against real business cases, measure quality honestly, and let the numbers settle arguments. * Handle the unglamorous parts well: error handling, fallbacks when a model misbehaves, latency, token cost, logging and monitoring. * Work with the engineers who own each codebase, fitting in with their patterns and pipelines rather than parachuting in something nobody else can maintain. * Keep up as models, tools and providers change, and choose pragmatically on quality, cost and latency rather than habit.