AI Quality and Evaluation Manager

Location: Hybrid working - Blackfriars 3 days per weekContract: 6 months, Outside IR35

Are you passionate about building the future of AI quality? Do you thrive in hands-on roles where you can shape frameworks from the ground up and make a real impact? We're looking for an experienced AI Quality & Evaluation Manager to join our team on a contract basis and lay the foundations for robust, reliable, and user-focused AI services across our business.

• Design and implement a comprehensive AI testing and evaluation framework for all AI solutions, including LLM-based tools, RAG systems, and third-party platforms.
• Define and document quality standards for semantic accuracy, factual consistency, bias, tone, and relevance.
• Develop reusable testing templates, data sets, and evaluation methods that can be scaled and maintained by internal teams.
• Run hands-on testing of AI prototypes and production tools to assess technical performance and business value.
• Collaborate with business users to guide practical testing and feedback processes.
• Deliver training and upskilling materials to empower internal staff to sustain the framework after your contract ends.
• Support vendor evaluations and POC assessments with robust test protocols.
• Establish baseline metrics and dashboards to measure ongoing AI quality and relevance.
• Work closely with engineering and product leads to embed testing into delivery workflows.
• Champion responsible AI practices to ensure fairness, transparency, and user trust.

• Strong hands-on experience in testing and evaluation of AI or software systems, ideally with NLP or LLM-based applications.
• Understanding of prompt evaluation, semantic search, and LLM behaviour (accuracy, hallucination, bias, tone, etc.).
• Familiarity with tools like Trulens, HumanLoop, PromptLayer, or similar; experience designing QA approaches for GenAI environments.
• Knowledge of modern AI architectures (RAG pipelines, embeddings, API integrations such as OpenAI, Azure OpenAI, Anthropic).
• Experience designing and implementing structured test regimes in fast-evolving contexts.
• Excellent communication and facilitation skills, engaging both technical and business audiences.
• Proven ability to create sustainable frameworks, documentation, and training materials.

• A builder who loves creating practical, scalable solutions.
• Hands-on and analytical, balancing experimentation with process.
• Collaborative and empathetic, bridging technical and non-technical teams.
• User-focused, driven by delivering real value.
• Committed to responsible AI, fairness, and transparency.

Ready to shape the future of AI quality with us?Apply now and help us ensure our AI-enabled services are accurate, consistent, and trusted by all.

Carbon60, Lorien & SRG - The Impellam Group STEM Portfolio are acting as an Employment Business in relation to this vacancy.