Senior WEM AQM Prompt Engineer

 

---

Five9 is one of the world's leading cloud contact center platforms. Our AI-powered Automated Quality Management (AQM) product is transforming how enterprises measure, evaluate, and improve agent and interaction quality at scale. As we build out our dedicated AQM Prompt Engineering capability within Specialized Services, we are hiring a Senior WEM AQM Prompt Engineer to lead and shape this practice.

This senior role goes beyond hands-on prompt design. You will be the technical authority for Five9 AQM prompt engineering — setting standards, building reusable assets, mentoring the Prompt Engineer team, and acting as the go-to expert for complex customer escalations and pre-sales engagements. If you have spent a significant portion of your career building sophisticated Speech Analytics programs in Verint, NICE, or Genesys — and you have developed serious prompt engineering skills alongside that domain expertise — this role was designed for you.

Why Your Speech Analytics Background is the Foundation for This Role
Building effective AQM prompts follows the same disciplined, iterative methodology that defines expert-level Speech Analytics category design:

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

At the senior level, this role adds a leadership and practice-building dimension: you will set the standards the rest of the Prompt Engineering team follows and serve as the technical authority across the most complex customer engagements.

Key Responsibilities — Practice Leadership
• Serve as the technical lead and subject matter authority for Five9 AQM Prompt Engineering within Specialized Services.
• Define and own the prompt engineering methodology, standards, quality gates, and best practice documentation for the team.
• Build and maintain a curated, reusable prompt library of validated evaluation templates spanning key verticals and QM use cases.
• Mentor and technically guide the WEM AQM Prompt Engineer team (x3), conducting prompt reviews and providing structured feedback.
• Drive continuous improvement of the team's prompt design process based on performance data, customer outcomes, and LLM platform developments.

Key Responsibilities — Customer Delivery
• Lead prompt engineering on the most complex and high-value AQM customer engagements, from initial scoping through production deployment.
• Act as the senior escalation point for prompt performance issues, failure analysis, and remediation on live customer deployments.
• Partner with customers at senior stakeholder level to translate QM strategy and compliance requirements into precise, measurable AQM evaluation criteria.
• Design and execute prompt validation frameworks — including representative call sampling, precision/recall analysis, and A/B prompt testing — to ensure accuracy before production release.

Key Responsibilities — Product & Pre-Sales Collaboration
• Serve as the Prompt Engineering SME in pre-sales engagements, demonstrating Five9 AQM capabilities and advising prospective customers on prompt-driven evaluation design.
• Provide structured product feedback to the Five9 AQM product team based on field experience, identifying gaps, limitations, and enhancement opportunities.
• Develop and deliver internal training and enablement for consultants and implementation staff on AQM prompt engineering techniques.
• Represent the Prompt Engineering practice in cross-functional forums and contribute to go-to-market materials, customer case studies, and thought leadership content.

Key Requirements
• Minimum 5 years' hands-on experience as a Speech Analytics Lead, Senior QM Analyst, or WEM Consultant with deep expertise in category/topic design, program governance, and optimization in Verint (Categories/Category Sets), NICE CXne (Category Sets), Genesys (Topics), or equivalent — at a seniority level sufficient to have owned or led an analytics program.
• Formal prompt engineering qualification or a verifiable, substantive portfolio of production-grade prompt design work, including evidence of iterative refinement, performance measurement, and documentation.
• Demonstrable understanding of LLM behavior — including how prompt structure, instruction framing, persona assignment, chain-of-thought, and few-shot examples affect model outputs.
• Strong background in Quality Management design: experience building evaluation frameworks, scorecard design, calibration processes, and QM governance.
• Experience leading or mentoring technical team members in a delivery or consulting environment.
• Proven track record of translating complex business requirements into structured, testable, and scalable technical solutions.
• Excellent written and verbal communication skills; comfortable presenting to senior client stakeholders and internal leadership.
• BA/BS or equivalent experience; advanced degree in a relevant discipline is advantageous.

Preferred Qualifications
• Formal prompt engineering certification: DeepLearning.AI Prompt Engineering for Developers, Anthropic Prompt Engineering, OpenAI Prompt Engineering, DAIR.AI Prompt Engineering Guide, or equivalent industry-recognized program.
• Direct experience with one or more leading LLM platforms at an advanced level (OpenAI GPT-4+, Anthropic Claude, Google Gemini, Meta Llama, or similar), including API usage, system prompt design, and evaluation harness development.
• Prior hands-on experience with Five9 AQM or another AI-native QM solution (e.g., NICE Enlighten QM, Genesys Cloud AI Quality, Medallia, Qualtrics).
• Experience contributing to or owning a Speech Analytics or QM center of excellence — including methodology documentation, internal training, and cross-client best practice standardization.
• Familiarity with prompt evaluation frameworks (e.g., LLM-as-judge, human-in-the-loop evaluation pipelines, or equivalent).
• Exposure to NLP concepts — tokenization, embeddings, semantic similarity — sufficient to reason about why a prompt succeeds or fails.
• Experience with JSON, Python scripting, or no-code automation tools as applied to prompt testing and workflow automation.
• Background in contact center compliance-driven QM (financial services, healthcare, utilities) where regulatory accuracy requirements add additional complexity to evaluation design.

Key Competencies
• Technical Authority — recognized internally and externally as the go-to expert on LLM prompt design for contact Centre quality evaluation.
• Analytical Rigor — applies statistical thinking and structured measurement to validate and continuously improve prompt performance.
• Linguistic Mastery — exceptional command of written instructio