Summary
Overview
Work History
Education
Skills
Accomplishments
Timeline
Generic

Vanessa Cornelius

Cape Coral,FL

Summary

Dynamic AI Prompt Engineer and QA strategist with 7 years of diverse experience in SaaS, AI, IoT, and conversational systems. Expertise in building robust evaluation frameworks and crafting production-grade system prompts while fostering collaboration with Product, Design, and Development teams. Renowned for integrating user empathy with technical precision, pioneering human-in-the-loop processes that ensure AI remains safe, intuitive, and dependable in real-world applications. Consistent history of delivering innovative solutions to complex challenges and driving significant enhancements in system performance.

Overview

6
6
years of professional experience

Work History

AI Prompt Engineer

OpenPhone
02.2024 - Current
  • AI Ownership 0→V2: Took the AI voice agent Sona from 0→1 and through V2, writing and iterating the full system prompt stack, job templates, triggers, and fallback logic.
  • Cross-Product Prompting: Personally authored and maintained all AI system prompts across OpenPhone’s product suite, ensuring consistency and safety beyond the voice agent.
  • Dual Role Execution: Delivered full QA ownership while driving prompt engineering — test planning, conducting regressions, triaging & filing bugs, retesting fixes, and ensuring release readiness — without compromise to either discipline.
  • Evaluation Framework: Built and maintained evaluation suite (Cekura, LLM-as-Judge) covering ambiguity, multi-intent, unsupported requests, sentiment handling, and performance.
  • Automation & Monitoring: Rolled out an AI testing framework integrated with TestMo; continuously monitored and iterated prompts to reduce fallback failures and improve job execution accuracy.
  • Cross-Functional Partner: Worked closely with Product, Design, and Engineering to align AI behaviors with roadmap goals and mitigate risks before development.
  • Human-in-the-Loop Advocate: Established evaluation cycles where human judgment validates AI output, ensuring safe, natural, and production-ready deployments.
  • Strengthened collaboration between QA, development, and product management teams through effective communication strategies.
  • Architected and scaled the AI evaluation framework underpinning all company-wide AI initiatives.

Senior QA Engineer

OpenPhone
02.2022 - Current
  • Migrated core VoIP & Messaging test repositories from TestRail → TestMo, streamlining test coverage.
  • Drove regression, mobile, and integration QA for major feature launches.
  • Reduced bug backlog by 39% through Linear board ownership and triage.
  • Recognized with “Most Value Delivered to Engineering” award for cross-squad impact.
  • Led QA initiatives, improving testing processes and implementing best practices for software validation.
  • Collaborated with cross-functional teams to identify and resolve software defects prior to release.
  • Reduced defect rates by conducting thorough root cause analysis and implementing corrective actions.
  • Played a key role in resolving critical defects during high-pressure situations, ultimately preserving client trust in company products and services.

Software QA Analyst

Radio Systems Corporation
02.2021 - 02.2022
  • Led QA on IoT/mobile integrations, executing regression suites across hardware + software.
  • Reduced test case bloat by 37% through optimized coverage.
  • Managed defect reporting process, ensuring clear communication with stakeholders regarding issue status and resolution timelines.
  • Expanded team knowledge base, mentoring junior QA analysts on best practices and industry standards.
  • Contributed to the establishment of performance benchmarks, tracking QA metrics over multiple development cycles.
  • Cut bug backlog by 52% with targeted cleanup & triage.

QC Engineer

Elavon
08.2020 - 08.2021
  • Audited large financial data sets for compliance; delivered reports to executive leadership.
  • Conducted root cause analysis and corrective action planning across 82% of all financial application errors- 100% reducing manual corrective follow- up action.

Test Engineering Senior Analyst

Accenture
04.2019 - 03.2020
  • Conversational AI QA Lead: Created test cases for Google Dialogflow and AI Manager projects.
  • Promoted to team lead managing 15+ analysts.
  • Optimized chatbot data coverage, improving NLP performance across multiple releases.
  • Led cross-functional testing initiatives to ensure software quality and compliance with client requirements.
  • Collaborated with developers to refine testing processes, improving efficiency of release cycles and reducing bottlenecks.

Education

B.S. - Organizational Leadership

Middle Tennessee State University
01.2018

Skills

  • Prompt Engineering & LLMs: System prompt design; Model evaluation metrics, Reinforcement learning, LM Fine-tuning, Conversational AI, Natural language processing
  • AI Product Quality: Evaluation framework design (Cekura/Vocera, LLM-as-Judge, TestMo integrations); prompt iteration cycles; Git version control, hallucination fallback risk reduction
  • QA & Testing: Playwright, Cypress, TestMo, TestRail, Mezmo, Heap, DataDog; API testing; regression & integration testing; usability & accessibility testing; IoT and multi-platform QA (iOS, Android, Web)
  • Collaboration Tools: GitHub, VS Code, JIRA, Linear, Confluence, Figma, Zeplin, LaunchDarkly
  • Leadership & Process: Agile/Scrum, cross-squad QA mentorship, risk assessment before development, human-in-the-loop workflows

Accomplishments

    Key Achievements

    • AI Leadership: Took OpenPhone’s AI voice agent Sona from 0→1 through V2, authored and

    iterated all AI system prompts across the product suite, and built the evaluation framework used

    company-wide.

    • Dual Ownership: Balanced full QA scope (test planning, regressions, bug triage, retesting) while

    driving AI prompt engineering and evaluation strategy — demonstrating unique ability to span

    disciplines without tradeoffs.

    • Awards & Recognition: Multiple company-wide value awards, including Relentless (twice), Most Value to Engineering, and Open.

Timeline

AI Prompt Engineer

OpenPhone
02.2024 - Current

Senior QA Engineer

OpenPhone
02.2022 - Current

Software QA Analyst

Radio Systems Corporation
02.2021 - 02.2022

QC Engineer

Elavon
08.2020 - 08.2021

Test Engineering Senior Analyst

Accenture
04.2019 - 03.2020

B.S. - Organizational Leadership

Middle Tennessee State University

Similar Profiles

CREATE PROFILE