WEM AQM Prompt Engineer

Role overview A specialized services team is building a new practice around LLM-driven quality evaluation for an AI-powered automated quality management (AQM) product. The role bridges contact center Quality Management domain expertise with applied AI, designing, testing, and optimizing the prompts that score agent performance against customer interactions. Three openings are available for analysts ready to apply disciplined speech-analytics rigor to prompt engineering.

Responsibilities - Design, author, and iteratively refine evaluation prompts, translating quality management frameworks into clear, testable LLM logic. - Partner with customers and delivery consultants during implementations to define evaluation scope, intent, and pass/fail criteria. - Select and analyze representative call samples to validate prompt performance, using precision and recall thinking to measure accuracy. - Maintain a versioned prompt library, documenting changes and managing prompts from initial design through production handover. - Collaborate with QA and Implementation teams to integrate prompt outputs into scoring forms, reporting, and broader QM workflows. - Identify failure patterns and apply structured debugging techniques such as chain-of-thought adjustments, instruction clarity improvements, and few-shot example tuning. - Contribute to internal standards, reusable templates, and best-practice documentation for the new capability. - Support pre-sales conversations by demonstrating prompt capabilities and explaining AI-driven quality evaluation to prospective customers.

Requirements - Minimum 3 years' hands-on experience as a Speech Analytics Analyst, QM Analyst, or WEM Application Consultant, with deep involvement in category or topic design across Verint, NICE CXone, Genesys, or comparable platforms. - Verifiable prompt engineering skills, demonstrated through formal coursework/certification or a portfolio of production prompts and iteration cycles. - Strong grounding in contact center Quality Management processes, evaluation frameworks, and scoring methodologies. - Experience selecting and analyzing interaction samples for model validation, comfortable with precision, recall, and F1-style measurement. - Excellent written communication skills, since prompt engineering is fundamentally a writing discipline. - Prior customer-facing or professional services experience; BA/BS or equivalent.

Nice to have - Hands-on experience with major LLM platforms (OpenAI, Anthropic Claude, Google Gemini, or similar), including direct API or playground usage. - Familiarity with JSON, basic scripting, or no-code automation tools for prompt testing workflows. - Exposure to AQM or AI-native QM solutions, or to platforms such as NICE Enlighten, Qualtrics, or Medallia. - Background developing training materials or internal knowledge base documentation. - Experience in compliance-driven QM environments such as financial services, healthcare, or utilities.

Benefits and work setup - Fully remote for candidates outside a 30-mile office radius; hybrid (3 days/week in office) for those within range. - US base salary range $70,400–$195,700, with potential annual performance bonus, stock, and other incentive plans. - Health, dental, and vision coverage from day one, with employer-paid employee premiums and shared dependent costs. - Short- and long-term disability, basic life insurance, and a 401(k) with employer matching. - Mental health support platform, employee stock purchase plan, paid time off, paid company holidays, paid volunteer hours, and 12 weeks paid parental leave.