Back

AI Prompt Engineer

Full-time

AI Prompt Engineer

We are Hiring

AI Prompt Engineer

with hands-on specialist responsible for designing, testing, deploying, and optimising 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/experience

  • Strong hands-on experience in LLM prompt engineering for production systems.

  • Experience with conversational AI for customer service (voice & 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/experience

  • Voice AI / IVA / IVR modernisation experience.

  • Experience in regulated industries (utilities, BFSI, public sector).

  • Exposure to contact-centre metrics such as containment, deflection, CSAT.

Image

Gazelle Global

AI Prompt Engineer

Image

Gazelle Global

AI Prompt Engineer

CX-Jobs is a free resource from Lorikeet, the AI support platform for complex, regulated businesses.

© 2026 Lorikeet. All rights reserved.

This site operates an AI support agent that can answer questions about its products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint:

GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}

Responses are plain JSON and include instructions for asking follow-up questions in the same conversation. Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.

CX-Jobs is a free resource from Lorikeet, the AI support platform for complex, regulated businesses.

© 2026 Lorikeet. All rights reserved.

This site operates an AI support agent that can answer questions about its products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint:

GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}

Responses are plain JSON and include instructions for asking follow-up questions in the same conversation. Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.

CX-Jobs is a free resource from Lorikeet, the AI support platform for complex, regulated businesses.

© 2026 Lorikeet. All rights reserved.

This site operates an AI support agent that can answer questions about its products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint:

GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}

Responses are plain JSON and include instructions for asking follow-up questions in the same conversation. Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.