V K Chaitanya D

• QA Leader with 17+ years of experience specializing in Generative AI (GenAI). Expertise in validating Conversational AI Chatbots and LLMs using advanced strategies including Prompt Engineering testing, A/B Testing, and Back-to-Back Testing to ensure model accuracy, safety, and perform.
• Proven track record in leveraging AI tools to accelerate the software development lifecycle, utilizing automated workflows to dynamically create, review, and maintain critical project artifacts
• Certified for PMP from PMI.
• Certified ISTQB Certified Tester - Foundation Level, ISTQB Certified Tester - AI Testing (CT-AI and ISTQB Certified Tester - Generative AI (CT-GenAI)
• Completed Azure AI-900 AI- Fundamentals certification
• Certified Scrum Master (CSM) from Scrum Alliance.
• 5+ years into AWS cloud and worked as Cloud Architect for project migration into AWS platform.
• Strategic QA Manager with 10+ years of expertise in team leadership and executive reporting. Proven track record of spearheading Left-Shift testing initiatives by architecting automation frameworks from scratch and integrating CI/CD pipelines (Git, Maven, Jenkins) early in the SDLC to streamline deployments and enhance software reliability
• Have worked in product based organizations for almost 12+ years.
• Experience in Restful API with Swagger and Postman.
• Hands-on Experience with Selenium Grid (Hub & Node).
• Experience in creating Ansible & Terraform scripts and setting up Test platforms by installing docker Microservices on AWS cloud services.
• Experienced in performance testing using SIPp and Jmeter, along with monitoring the test using New Relic and Prometheus & Grafana.
• 6+ years into SaaS applications.
• Onsite 2 years of experience with Verizon Client in Colorado Springs, United States.
• Have B1 VISA valid till 2026.
• On call support experience in the Production environment as L4 engineer and interacting with customers.
• Experienced in OSS/BSS platform validation and maintaining in Production environment.
• Have working experience with Application layer protocols both in functional and non-function testing.
• Possess testing expertise in protocols SS7 and SIP (VoIP).
• Extensive experience in IP Contact Center Architecture (CCaaS) which includes IPTF & IP IVR calls and Unified Communication (UC) architectures (UCaaS). Used 3G protocols.
• IP IVR and IP TF call processing scenarios end to end testing including backend Unix server verification.
• Led QA Team in Legacy platform migration to cloud environment using Agile methodology.
• Have in-depth working experience in STLC, SDLC processes.
• Rich experience in Tools like HP ALM and JIRA & Zephyr for tracking and delivering the Projects.
• Analytical thinker that consistently narrows down the ongoing issues or defects in both Test and Production Environment.

Multi-talented Senior Manager well-versed and highly effective at developing, executing and directing key improvements to enable business enhancements and growth. Visionary leader with solid success leading business operations toward growth.

• GenAI R & D Product, Validated a GenAI product which was in the R & D stage, has been certified to release into production ENV as per business requirements in span of 4 months only.
• Ansible & Terraform, By creating & implementing the DEV & Test platform using Terraform and Ansible scripts based on Docker microservices, was able to streamline the code installation and significantly reduced install time from 2 days to 2 hours.
• Project Migrations to Cloud Platform, Have migrated VCB legacy project into AWS cloud platform and have reduced production implementation and maintenance cost to the company.
• Promise Management Product, Spearheaded the new product UAA validation, resulting in opening up new market space for the company.

• Appreciation Cert. for exceptional Skills and Hard work, Shell, 02/01/25
• OUTSTANDING PERFORMANCE AWARD, Uniphore Software Systems, 01/01/22
• OUTSTANDING PERFORMANCE AWARD, Uniphore Software Systems, 06/01/22
• TEAM SPOT AWARD, Verizon, 07/01/15
• STAR PERFORMER AWARD, Infinite Computer Solutions, 07/01/09

VSME – Virtual Subject Matter Expert | Shell 

Product Overview : Led the end-to-end quality assurance for VSME, a flagship Generative AI product leveraging NLP and Retrieval-Augmented Generation (RAG). The platform enables conversational AI to extract high-fidelity data from massive datasets, including text, tables, and images, integrated with ChatGPT for enhanced accuracy.

Key Contributions & Impact:

• Strategic QA Leadership: Spearheaded the testing lifecycle for 8 diverse LLM use cases including LNG, Wells, Aviation, and HR, ensuring cross-domain model reliability.
• Advanced AI Validation: Architected and executed specialized testing methodologies, including A/B Testing, Back-to-Back Testing, and citation validation to eliminate hallucinations and ensure factual AI responses.
• Cloud Operations: Managed test execution and monitoring on Azure DevOps, validating product architecture, EPICs, and user stories.
• Deployment & Sign-off: Directed "Go/No-Go" decision-making meetings, providing final QA sign-off for production releases and managing post-deployment On-Call support for critical escalations.
• Efficiency Gains: Streamlined the transition from R&D to Production within a 4-month window while managing a full-stack QA team.

Shell-E Platform | Shell

Product Overview: Shell-E is an enterprise GenAI platform designed to develop and deploy Large Language Model (LLM) based applications quickly and safely. The platform offers plug-and-play capabilities to transform business processes, featuring custom prompt-based applications, multi-agent systems, and RAG pattern-based knowledge retrieval to accurately query large volumes of multi-modal text and image data.

Key Contributions & Impact:

• End-to-End QA Management: Spearheaded the comprehensive quality assurance lifecycle for the Shell-E platform, managing test strategies from initial data ingestion to production-ready deployment.
• Advanced Prompt & A/B Testing: Formulated specialized testing methodologies, including systematic Prompt Engineering testing and A/B testing, to optimize LLM outputs, minimize hallucinations, and evaluate model performance across varied business use cases.
• Automation Framework Engineering: Designed and executed robust automation test suites to validate plug-and-play RAG architectures, ensuring high-fidelity retrieval accuracy across massive multi-modal (text and image) datasets.
• Multi-Agent & RAG Validation: Directed end-to-end integration and verification workflows for complex multi-agent applications, establishing strict safety guardrails and secure deployment gates.

U-Assist & U-Self Serve Products

Product Overview:Led QA initiatives for the U-Assist platform, an AI-driven automation suite for contact centers. The platform leverages Artificial Intelligence to predict customer sentiment and intent, improving First Contact Resolution (FCR) through real-time agent coaching and reducing After Contact Work (ACW) via automated summarization and redaction.

Key Contributions & Impact:

• Infrastructure & DevOps: Architected and deployed test environments on AWS Cloud using Ansible scripts and Docker microservices, ensuring a scalable and reproducible testing infrastructure.
• Automation Leadership: Designed and implemented a robust Cucumber (BDD) automation framework, overseeing the execution and maintenance of scripts to accelerate delivery cycles.
• Performance Engineering: Conducted comprehensive benchmarking using JMeter, implementing real-time performance monitoring with Prometheus and Grafana to identify system bottlenecks.
• Agile Governance: Managed the end-to-end testing lifecycle by reviewing EPICs, drafting User Stories, and conducting peer reviews for integration-level test cases.
• Release Management: Played a critical role in Go/No-Go meetings, providing technical validation for production deployments and maintaining system stability through On-Call support for client escalations.
• Feature Innovation: Actively collaborated on new feature development, integrating emerging technologies to enhance the platform’s sentiment analysis and alerting capabilities.

U-Assist Assurance (UAA) – Promise Management 

Product Overview:UAA is an AI-driven extension of the U-Assist suite, focusing on automated Promise Management. The platform uses AI models to detect and classify commitments (Monetary, Communication, Delivery) from live agent transcripts, integrating with CRMs and third-party bots to track fulfillment status.

Key Contributions & Impact:

• Infrastructure as Code (IaC): Architected the test environment on AWS using Terraform and Ansible to deploy Docker microservices, significantly reducing environment setup time and ensuring parity between Dev and QA.
• Strategic Product Influence: Analyzed product scope and functional impacts to provide high-level recommendations to Product Owners, directly shaping the feature roadmap.
• Advanced Automation: Designed and implemented a Cucumber (BDD) automation framework, leading the execution and maintenance of scripts to ensure rapid regression cycles.
• Performance Benchmarking: Conducted rigorous performance testing using JMeter, utilizing Prometheus and Grafana for real-time monitoring and bottleneck analysis.
• Release Governance: Served as a key stakeholder in "Go/No-Go" meetings, ensuring zero-defect deployments for production environments.
• Technical Leadership: Guided the team through complex test activities, reviewed technical approaches, and supported Product Owners during high-stakes client demonstrations.