Senior Applied AI Engineer – Prompting & Evaluation

Klipsboard is a global, growing business that embraces AI and emerging technologies to enhance customer outcomes, collaboration, and continuous improvement. The company offers flexible hybrid work, with three days in office and two days remote, across offices in the UK, Ireland, The Netherlands, South Africa, Kenya, and North America.

• Design, build, and refine prompts, context strategies, and agentic workflows for AI features in Klipsboard products.
• Coaching, pairing, and workshops to elevate engineers’ AI capabilities across UK and South Africa teams.
• Define and uphold standards for prompting, evaluation, and context engineering, adapting them as tools change.

• Large language model APIs (GPT, Claude, Llama, etc.)
• AI coding tools (Git Hub Copilot, Cursor, and equivalents)
• Prompt engineering, context design, and agentic workflow frameworks
• Evaluation harnesses, datasets, and automated test suites for AI outputs
• Retrieval-augmented generation, vector search, embeddings, and retrieval pipelines (desirable)
• LLM orchestration frameworks (Lang Chain, Semantic Kernel, etc.) (desirable)

• Strong software engineering background with several years of production software delivery.
• Hands‑on experience with large language models: prompt design, context engineering, structured outputs.
• Experience building evaluation or test harnesses for LLM outputs and using them to improve quality measurably.
• Clear evidence of mentoring or teaching other engineers.
• Daily fluency with AI coding tools such as Git Hub Copilot or Cursor.

• Deliver AI features with proper evaluation and measurable quality standards.
• Embed prompt engineering and evaluation best practice across R&D.
• Maintain high standards for safety, accuracy, and data handling.
• Build and sustain a library of prompt patterns, templates, and guides.
• Deliver coaching tailored to engineers at all maturity levels.

• Ensure AI features provide accurate, safe, and trustworthy answers.
• Work with product teams and subject matter experts to understand each feature’s business problem.
• Prevent confidently wrong answers such as incorrect prices, part matches, or stock levels.

• Engineers across teams visibly improve due to coaching and knowledge‑sharing.
• At least one AI feature or workflow shipped per quarter with proper evaluation.
• A living, use‑oriented library of prompt patterns and guides.
• A well‑attended community of practice producing reusable outputs.
• Engineering leadership has a clear, evidence‑based view of AI impact.

• Generous with knowledge and energized by others improving.
• Rigorous, honest about results and data.
• Patient across all AI maturity levels.
• Curious about Klipsboard customers’ trades.
• Calm toward rapid model and tooling change.
• Close collaboration with engineering leadership, architecture, product, and cross‑site teams.

• Travel between UK and South Africa offices for coaching and community building.
• Keep standards current as models, tools, and providers evolve.
• Represent Klipsboard’s engineering practice externally (talks, writing, open‑source).

Internal:
Engineering leadership and architecture teams; R&D engineering teams across Newcastle, Tankersley, Hungerford, Johannesburg and Cape Town/Stellenbosch;
Product managers and owners;
Subject matter experts in distributive trades, rental, automotive.

External: AI and LLM platform and tooling providers (as needed).

• Strong software engineering background with several years of production software delivery.
• Substantial hands‑on experience with LLMs: prompt design, context engineering, structured outputs.
• Experience building evaluation or test harnesses for LLM outputs.
• Clear evidence of mentoring or teaching other engineers.
• Daily fluency with AI coding tools like Git Hub Copilot or Cursor.

• Experience with retrieval‑augmented generation, agentic workflows, tool use or…