Krishna Mohan B — Senior QA Engineer

Krishna Mohan B

Senior QA Engineer

AI/LLM Test Engineer • Automation QA

Senior QA Engineer with 5 years of experience in Manual Testing, API Testing, Automation, and AI/LLM application testing. Experienced in validating enterprise web applications, APIs, automation frameworks, AI-powered systems, and computer-vision solutions with a strong focus on reliability, quality, and production readiness.

📍 Hyderabad•Immediate Joiner•Open to Remote / Hybrid
Download Resume View Projects LinkedIn GitHub Email
05Years Experience
0+Cameras Validated
0+AI Benchmark Cases
Portrait of Krishna Mohan B
Krishna Mohan B
Senior QA Engineer AI/LLM Test Engineer Automation QA
01 — About

Professional Summary

A quick summary of experience and core focus areas.

I ensure software quality through manual, API, automation, and AI/LLM testing. My experience spans enterprise web applications, APIs, automation frameworks, AI/RAG systems, and computer-vision solutions. I focus on building effective test strategies, scalable automation, and reliable quality processes that identify issues early and support production-ready releases.

Core focus areas
  • AI / LLM & agent testing
  • RAG evaluation & hallucination testing
  • Computer-vision testing
  • API & automation testing
  • Functional & regression testing
  • Quality engineering & release strategy
02 — Skills

Skills & Tools

Tools and technologies used across the QA lifecycle.
AI / LLM Testing
🗂 Golden Datasets🔍 RAG Evaluation ⚠️ Hallucination Testing🤖 Promptfoo🧠 DeepEval📈 Precision / Recall
Automation
🧭 Selenium WebDriver🎭 Playwright✅ TestNG🧩 Hybrid POM
API & Database
📬 Postman🔗 Rest Assured🗄 SQL
CI/CD & QA Tools
🔧 Jenkins🌿 Git🐳 Docker📌 JIRA🔁 Agile / Scrum
03 — Method

How I Approach Quality Engineering

The pipeline behind every benchmark and bug report.
01
RequirementsScope, acceptance criteria & edge cases
02
Test PlanningStrategy, risk areas & coverage plan
03
Quality EngineeringManual + API + UI
04
Test AutomationSelenium + Playwright + API
05
AI Quality ValidationLLM + RAG + Prompt + Citation
06
Quality MetricsAccuracy + coverage + defect trends
07
Release ValidationRegression + UAT + sign-off
04 — Log

Experience

Most recent first.
QA Engineer II Current
Masterworks — Nabeh AI Division · Feb 2026 – Present
  • Created 120+ benchmark ("golden") test cases for evaluating AI agent accuracy, grounding, and hallucination.
  • Evaluated precision, recall, and hallucination-related metrics using Promptfoo and DeepEval across multiple insurance AI agents.
  • Validated conversational AI / voice-bot functionality including intent recognition, NLP, and speech-to-text.
  • Built and maintained an AI test-generation agent for creating test plans, scenarios, test cases, and pass/fail dashboards.
  • Extended the agent to execute against applications and generate structured QA/defect reports.
  • Developed automated API tests using Postman and Rest Assured across Agile sprints and documented QA findings for stakeholders.
Sr. Software Test Engineer
ZestIoT Technologies Pvt. Ltd. · Nov 2021 – Feb 2026
  • Validated 1000+ cameras for AI-powered monitoring and event detection across a microservices/Docker architecture.
  • Designed vision / OCR test assets for computer-vision QA.
  • Built and owned a Selenium WebDriver automation framework using hybrid POM and data-driven testing; working knowledge of Playwright.
  • Developed automated API tests using Postman and Rest Assured; performed backend SQL validation and root-cause analysis.
  • Executed functional, regression, integration, and UAT testing across release cycles.
  • Mentored junior QA engineers on automation, testing best practices, and bug reporting.
Bachelor of Engineering, Computer Science
Kalinga University, India
2016 – 2020
05 — Evidence

Projects

Public repos — source linked, not just claimed.
QA-Agent Featured
Problem Manual QA teams spend significant time creating test cases, tracking defects, and re-testing fixes.
Solution An AI-powered QA copilot that converts specifications into traceable test cases and supports real browser, API, and database validation.
My role Independent developer — architecture, agent design & test-execution engine.
  • Generates traceable test cases & RTMs directly from BRD/PRD/API docs
  • Executes real Playwright, API, and read-only database checks — not mocked
  • Auto-drafts defects from actual failures and re-verifies fixes on re-run
  • Builds AI/RAG benchmark datasets with optional Jira sync
GitHub — View source →
Promtfoo_Playwright evaluation pipeline: load dataset, login, create chat, ask agent, parse stream, grade answer, export report
Promtfoo_Playwright RAG Evaluation
Problem Multi-agent RAG chat APIs need repeatable semantic evaluation, not only basic API or uptime checks.
Solution A Promptfoo-based evaluation pipeline that runs benchmark questions, processes responses, and evaluates them against expected references.
  • Ships with a mock multi-agent API + 120-question sample dataset
  • Automates login → ask → parse-stream → grade → export report end-to-end
GitHub — Source →
API-Automator-XLS API Testing
Problem Teams need a simple way to author and execute API test cases without writing every test manually.
Solution Excel-driven API automation that executes API tests through Newman and generates structured test reports.
  • Zero-code test authoring for non-engineers
  • Three parallel report formats (HTML / Allure / Excel) from one run
GitHub — Source →
06 — Achievements

What I Deliver

Outcomes, not adjectives.
05 Years of QA experience
0+ AI benchmark cases created
0+ Computer-vision cameras validated