Role overview
We are seeking an experienced and innovative Head of AI Prompt Engineering to lead the development and optimisation of AI-driven systems within a new SaaS product. This role combines technical AI expertise, product thinking, and leadership capability.
You will architect prompt strategies, design scalable AI workflows, oversee model optimisation, and lead the AI development direction from concept to deployment.
This is a leadership role for someone who understands both large language models (LLMs) and commercial SaaS product delivery.
What we're looking for
- Design and own the AI prompt engineering framework across the SaaS platform
- Develop structured prompt libraries and reusable AI workflows
- Implement multi-step reasoning chains and advanced prompt chaining
- Evaluate and integrate LLMs (OpenAI, Anthropic, open-source models, etc.)
- Establish quality control systems for AI outputs
- Product Development
- Work closely with product and engineering teams to embed AI into core features
- Translate business goals into AI-driven solutions
- Lead AI feature ideation, prototyping, testing, and iteration
- Optimise latency, cost efficiency, and model performance
- AI Optimisation & Performance
- Develop testing frameworks for prompt reliability and consistency
- Reduce hallucinations and improve contextual accuracy
- Implement guardrails and safety mechanisms
- Monitor token usage and optimise cost structures
- Leadership & Team Management
- Build and lead a small AI/prompt engineering team
- Establish best practices and documentation standards
- Mentor junior engineers
- Collaborate with data engineers, backend developers, and UX teams
Required Skills & Experience
- 3+ years working with LLMs and AI systems
- Strong experience with prompt engineering at production level
- Deep understanding of:
- GPT-based models
- Prompt chaining & reasoning frameworks
- RAG (Retrieval-Augmented Generation)
- Embeddings & vector databases
- Experience in SaaS product development lifecycle
- Familiarity with APIs and backend integration (Python, Node.js preferred)
- Strong analytical and problem-solving skills
- Experience implementing AI guardrails and testing frameworks
- Experience leading AI projects from MVP to scale
- Experience with fine-tuning or training custom models
- Knowledge of LangChain, LlamaIndex, or similar frameworks
- Background in machine learning or computer science
- Experience optimising AI systems for cost and performance
- Startup or scale-up experience
Key Competencies
- Strategic thinker
- Highly analytical
- Commercially aware
- Leadership mindset
- Strong communicator
- Detail-oriented with systems thinking
KPIs / Success Metrics
- AI feature deployment timelines
- Output accuracy and quality benchmarks
- Reduction in hallucination rates
- Token cost optimisation
- User engagement with AI-driven features
- Successful launch of SaaS AI core product
What We Offer
- Opportunity to lead AI innovation from the ground up
- Equity participation (for the right candidate)
- Competitive salary
- Flexible working
- High-growth SaaS environment
Job Types: Full-time, Permanent
Pay: £46,205.96-£126,026.60 per year
Work Location: In person
Tags & focus areas
Used for matching and alerts on DevFound Fulltime Ai Generative Ai