Design, test, and optimise the prompts and agent workflows that power WizQuest's AI-native delivery and client products.
Responsibilities
- Design and refine prompts for code generation, analysis, and automation
- Build and evaluate multi-step agent workflows and tool use
- Create evals and test harnesses to measure prompt quality and reliability
- Optimise for accuracy, safety, latency, and token cost
- Document prompt patterns and share best practices across pods
Requirements
- 2+ years working with LLMs (Anthropic/OpenAI) in real applications
- Strong written communication and structured, systematic thinking
- Comfortable with Python and API integration
- Experience with prompt evaluation, RAG, or agent frameworks
- Bonus: a software development background
How to apply: Send your resume to career@wizquest.io with the role title in the subject line.