Five9 logo
Five9
Posted 75 days agoVerified live 14h ago

WEM AQM Prompt Engineer

Brief overview

Remote
UndergradOr in progress
$70k–$196k/yrStated range
3+ yrsMinimum
39 H-1B approvalsDept. of Labor
15 green cardsCertified filings
Speech AnalyticsVerint CategoriesNICE Category SetsGenesys TopicsPrompt EngineeringContact Center Quality ManagementEvaluation FrameworksPrecision and Recall MetricsLLM PlatformsJSONScriptingAnalytical Rigor

About the company

Five9 is a cloud-based call center software company that specializes in sales, marketing, and customer service. It is a sub-organization of Five Rivers Solutions.

Visa sponsorship history

4 years sponsoring, last filed FY2026

Data powered by U.S. Department of Labor. This does not guarantee sponsorship for this specific role.
39H-1B approved
98%approval rate
2new H-1B hires
15PERM certified
$184,330median wage / yr
H-1B Petition ApprovalsVisas USCIS actually granted: the strongest sign the company sponsors.
202312
202415
20258
20264
LCA Certified ApplicationsAn early filing step, not a visa approval: it signals intent, not confirmed sponsorship.
20233
20252
20264
Green Card (PERM) FilingsCertified green card filings: a long-term commitment to international hires.
20232
20244
20259
Top sponsored roles
Network Engineer “ OperationsPrincipal Program ManagerSenior Director, Product ManagementNetwork EngineerSenior Manager, Cloud Engineering
Sponsored employees from
IndiaCanadaRussia

Job description

Summary

Five9 is a leading provider of cloud contact center software, bringing the power of cloud innovation to customers worldwide. They are seeking WEM AQM Prompt Engineers to design, test, and optimize the LLM prompts that power Five9 AQM's automated evaluation criteria, leveraging expertise in Speech Analytics. The role involves collaborating with customers and internal teams to implement quality management frameworks effectively.

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

Skills

  • Minimum 3 years' hands-on experience as a Speech Analytics Analyst, QM Analyst, or WEM Application Consultant with deep involvement in category/topic design and optimization in Verint (Categories/CategorySets), NICE (Category Sets), Genesys (Topics), or equivalent platforms
  • Demonstrable prompt engineering skills — either via formal qualification or a verifiable portfolio of prompt design work (production prompts, evaluation outputs, or documented iteration cycles)
  • Strong understanding of contact center Quality Management processes, evaluation frameworks, and scoring methodologies
  • Experience selecting and analyzing call/interaction samples for model validation; comfortable applying precision, recall, and F1-score thinking to prompt performance measurement
  • Proven ability to translate business and QM requirements into structured, testable evaluation logic
  • Excellent written communication skills — prompt engineering is fundamentally a writing discipline
  • Experience working in a customer-facing or professional services environment
  • BA/BS or equivalent experience
  • Formal prompt engineering certification or coursework (e.g., DeepLearning.AI Prompt Engineering for Developers, Anthropic Prompt Engineering certification, OpenAI Prompt Engineering course, or equivalent)
  • Hands-on experience with one or more major LLM platforms (OpenAI, Anthropic Claude, Google Gemini, or similar) including direct API or playground usage
  • Prior exposure to Five9 AQM or equivalent AI-native QM solutions
  • Experience with NICE Enlighten, Qualtrics, Medallia, or other AI-driven analytics platforms
  • Familiarity with JSON, basic scripting, or no-code automation tools — useful for prompt testing workflows
  • Experience developing training materials or internal knowledge base documentation
  • Background in compliance-driven QM environments (financial services, healthcare, utilities)

Qualifications

Must Haves

  • Minimum 3 years' hands-on experience as a Speech Analytics Analyst, QM Analyst, or WEM Application Consultant with deep involvement in category/topic design and optimization in Verint (Categories/CategorySets), NICE (Category Sets), Genesys (Topics), or equivalent platforms
  • Demonstrable prompt engineering skills — either via formal qualification or a verifiable portfolio of prompt design work (production prompts, evaluation outputs, or documented iteration cycles)
  • Strong understanding of contact center Quality Management processes, evaluation frameworks, and scoring methodologies
  • Experience selecting and analyzing call/interaction samples for model validation; comfortable applying precision, recall, and F1-score thinking to prompt performance measurement
  • Proven ability to translate business and QM requirements into structured, testable evaluation logic
  • Excellent written communication skills — prompt engineering is fundamentally a writing discipline
  • Experience working in a customer-facing or professional services environment
  • BA/BS or equivalent experience

Nice to Haves

  • Formal prompt engineering certification or coursework (e.g., DeepLearning.AI Prompt Engineering for Developers, Anthropic Prompt Engineering certification, OpenAI Prompt Engineering course, or equivalent)
  • Hands-on experience with one or more major LLM platforms (OpenAI, Anthropic Claude, Google Gemini, or similar) including direct API or playground usage
  • Prior exposure to Five9 AQM or equivalent AI-native QM solutions
  • Experience with NICE Enlighten, Qualtrics, Medallia, or other AI-driven analytics platforms
  • Familiarity with JSON, basic scripting, or no-code automation tools — useful for prompt testing workflows
  • Experience developing training materials or internal knowledge base documentation
  • Background in compliance-driven QM environments (financial services, healthcare, utilities)

Benefits

  • Annual performance bonus
  • Stock
  • Other applicable incentive compensation plans
  • Health, dental, and vision coverage, beginning on the first day of employment
  • Five9 covers 100% of the employee portion of the health, dental and vision coverage and shares a high portion of the dependent cost
  • Short & Long-Term Disability
  • Basic Life Insurance
  • 401k saving plan with employer matching
  • Access to an innovative mental health support platform that offers personalized care and resources in areas such as: therapy, coaching and self-guided mindfulness exercises for all covered employees and their covered dependents
  • Generous employee stock purchase plan
  • Paid Time Off
  • Company paid holidays
  • Paid volunteer hours
  • 12 weeks paid parental leave

More jobs like this