Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Software engineer with over 30 years of commercial development experience, now specialising in AI systems evaluation, LLM assessment, AI red teaming, and Retrieval-Augmented Generation (RAG). I design, test, evaluate, and improve AI-powered applications, conversational agents, and LLM output quality with a strong focus on reliability, safety, and user experience. Through AgentK ai and client work (including Wallowfish), I assess AI systems under real-world and adversarial conditions—covering prompt injection attempts, conflicting instructions, hallucinations, retrieval failures, and edge-case conversational flows—before they reach production.…Software engineer with over 30 years of commercial development experience, now specialising in AI systems evaluation, LLM assessment, AI red teaming, and Retrieval-Augmented Generation (RAG). I design, test, evaluate, and improve AI-powered applications, conversational agents, and LLM output quality with a strong focus on reliability, safety, and user experience. Through AgentK ai and client work (including Wallowfish), I assess AI systems under real-world and adversarial conditions—covering prompt injection attempts, conflicting instructions, hallucinations, retrieval failures, and edge-case conversational flows—before they reach production.

Clive Smart

AI Prompt Engineer, AI Engineer, AI Developer, +4





Software engineer with over 30 years of commercial development experience, now specialising in AI systems evaluation, LLM assessment, AI red teaming, and Retrieval-Augmented Generation (RAG). I design, test, evaluate, and improve AI-powered applications, conversational agents, and LLM output quality with a strong focus on reliability, safety, and user experience. Through AgentK ai and client work (including Wallowfish), I assess AI systems under real-world and adversarial conditions—covering prompt injection attempts, conflicting instructions, hallucinations, retrieval failures, and edge-case conversational flows—before they reach production.…Software engineer with over 30 years of commercial development experience, now specialising in AI systems evaluation, LLM assessment, AI red teaming, and Retrieval-Augmented Generation (RAG). I design, test, evaluate, and improve AI-powered applications, conversational agents, and LLM output quality with a strong focus on reliability, safety, and user experience. Through AgentK ai and client work (including Wallowfish), I assess AI systems under real-world and adversarial conditions—covering prompt injection attempts, conflicting instructions, hallucinations, retrieval failures, and edge-case conversational flows—before they reach production.

Available to hire

Software engineer with over 30 years of commercial development experience, now specialising in AI systems evaluation, LLM assessment, AI red teaming, and Retrieval-Augmented Generation (RAG). I design, test, evaluate, and improve AI-powered applications, conversational agents, and LLM output quality with a strong focus on reliability, safety, and user experience.

Through AgentK ai and client work (including Wallowfish), I assess AI systems under real-world and adversarial conditions—covering prompt injection attempts, conflicting instructions, hallucinations, retrieval failures, and edge-case conversational flows—before they reach production.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

Freelance AI Consultant — AgentK ai & client projects at AgentK ai & client projects

January 1, 2022 - Present

Conducts AI system evaluation and AI red teaming with a focus on LLM evaluation, prompt engineering and prompt-injection testing, RAG evaluation, and agent workflow assessment. Works on hallucination and output quality assessment, response quality testing, and workflow reliability checks under adversarial and edge-case scenarios. Includes evaluation of API and data-base integrations and prompt optimization, ensuring AI systems behave safely and consistently before production rollout.

Head of IT at Beau Ty Training Int Ltd

January 1, 2017 - Present

Lead IT function and support development/operation of AI-powered student support and customer support systems. Conduct AI system evaluation and chatbot testing, and integrate AI assistance into CRM/LMS. Drive workflow automation and ongoing improvements to conversational and support tooling.

Head of IT — Beauty Training Int Ltd at Beauty Training Int Ltd

January 1, 2017 - Present

Leads IT and supports development of AI-powered student support and customer support chatbots. Performs AI-related evaluation and chatbot testing, including conversational quality improvements. Handles CRM and LMS integrations and workflow automation to improve service delivery and operational efficiency.

Head of IT at Producte ch Ltd

January 1, 2009 - Present

Provide software architecture leadership and platform development oversight, including reporting/analytics and automation systems. Contribute to AI-assisted recommendation systems and deliver technical leadership across development and operations for production systems.

Head of IT — Productecch Ltd at Productecch Ltd

January 1, 2009 - Present

Provides software architecture, platform development and technical leadership. Oversees reporting and analytics, automation systems, and implementation of AI-assisted recommendation systems. Leads technical direction for building and maintaining platforms and integrating automation and analytics capabilities.