Job Opportunities API

Join us in bringing joy to customer experience.  Five9 is a leading provider of cloud contact center software, bringing the power of cloud innovation to customers worldwide.    Living our values everyday results in our team-first culture and enables us to innovate, grow, and thrive while enjoying the journey together. We celebrate diversity and foster an inclusive environment, empowering our employees to be their authentic selves.    Five9 is one of the world's leading cloud contact center platforms, and our AI-powered Automated Quality Management (AQM) product is transforming how enterprises evaluate and improve agent performance. To support the accelerating adoption of Five9 AQM across our customer base, the Specialized Services team is building a dedicated Prompt Engineering practice. We are seeking three WEM AQM Prompt Engineers to join this new capability team. These roles sit at the intersection of contact center domain expertise and applied AI — designing, testing, and optimizing the LLM prompts that power Five9 AQM's automated evaluation criteria. If you have spent years building Speech Analytics categories in Verint, category sets in NICE, or Topics in Genesys, you already think and work the way this role requires. Why Your Speech Analytics Experience Maps Directly to This Role The Five9 AQM Prompt Engineering workflow follows the same disciplined, iterative process that experienced Speech Analytics analysts use every day: Speech Analytics / Verint AQM Five9 AQM Prompt Engineering Define category intent & scope  Define prompt intent & evaluation scope Select & tag representative call samples  Select evaluation call samples Iteratively tune keyword / phrase sets  Iteratively refine prompt wording & logic Test against live call traffic  Test prompt outputs against real calls Validate recall & precision metrics  Validate pass / fail accuracy metrics Document & hand off to QA team  Document prompts for QA workflow Key Responsibilities • Design, author, and iteratively optimize LLM evaluation prompts within Five9 AQM, translating quality management frameworks into accurate, testable prompt logic. • Partner with customers and internal delivery consultants during AQM implementation engagements to define evaluation scope, intent, and pass/fail criteria. • Select and analyses representative call samples to validate prompt performance; apply precision and recall thinking to measure and improve prompt accuracy. • Maintain a structured prompt library — versioning prompts, documenting changes, and managing prompt lifecycle from initial design through to production handover. • Collaborate with QA and Implementation teams to integrate prompt outputs into broader QM workflow design, including scoring forms and reporting. • Identify prompt failure patterns and apply structured debugging techniques, including chain-of-thought adjustments, instruction clarity improvements, and few-shot example tuning. • Contribute to the development of Five9 AQM prompt engineering standards, best practice documentation, and reusable prompt templates. • Support pre-sales activities by demonstrating Five9 AQM prompt capabilities and articulating the value of AI-driven quality evaluation to prospective customers. • Stay current with LLM developments, prompt engineering research, and the evolving Five9 AQM product roadmap. Ideal Candidate Profile The strongest candidates will come from a Speech Analytics background with hands-on experience designing and optimizing categories, category sets, or topic models in platforms such as Verint, NICE CX one, or Genesys — and who are ready to apply that same analytical rigor to LLM prompt design. Key Requirements • Minimum 3 years' hands-o