The Role:
The AI Prompt Engineer is a hands-on specialist responsible for designing, testing, deploying, and optimizing prompts and agentic workflows for multi-channel customer service AI solutions. The role blends conversational design, LLM prompt engineering, evaluation discipline, and production-grade governance.
Your responsibilities:
- Design and iterate prompts for IVR, voice bots, chatbots, and messaging channels.
- Build agentic AI workflows using tool calling, orchestration, and multi-step reasoning.
- Define and maintain prompt evaluation frameworks, regression test suites, and quality metrics.
- Implement guardrails for safety, compliance, PII handling, and hallucination reduction.
- Integrate AI prompts with CRM, knowledge bases, billing, and contact-centre platforms.
- Partner with CX, Product, Engineering, and SMEs to translate journeys into AI behaviour.
- Monitor production performance using analytics and continuously optimise outcomes.
- Manage prompt versioning, approvals, and release processes across environments.
- Support UAT, go-live, and early-life support phases.
- Contribute reusable prompt patterns, playbooks, and accelerators.
Essential skills, knowledge, and experience:
- Strong hands-on experience in LLM prompt engineering for production systems.
- Experience with conversational AI for customer service (voice and chat).
- Knowledge of agentic AI design patterns and orchestration.
- Experience with RAG, grounding techniques, and prompt evaluation.
- Understanding of Responsible AI, security, and compliance controls.
- Familiarity with Git, CI/CD concepts, and release governance.
- Strong stakeholder communication skills.
Desirable skills, knowledge, and experience:
- Voice AI, IVA, and IVR modernisation experience.
- Experience in regulated industries (utilities, BFSI, public sector).
- Exposure to contact-centre metrics such as containment, deflection, and CSAT.
