Venkateshwara Doijode - AI Automation Architect

// about

Crafting quality at enterprise scale

I'm a Senior SDET and Automation Architect with nearly a decade of hands-on experience building quality platforms that don't just test software — they accelerate it. My work lives at the intersection of intelligent automation, AI/LLM-augmented testing, and DevOps engineering.

At Wipro/BNY, I led the redesign of an entire regression ecosystem — compressing a 4-hour test suite to under 45 minutes, integrating AI-assisted self-healing logic, and building the Eliza AI Agent to eliminate data lookup bottlenecks across QA teams. I've since extended that work into full AI/LLM testing frameworks — using Python, PyTest, Promptfoo, and RAGAS to evaluate accuracy, relevance, hallucination, and response quality, and running RAG, agent, robustness, bias, metamorphic, and drift evaluations as quality gates inside CI/CD.

Beyond my day-to-day role, I design custom MCP servers and agentic tooling to close real gaps in QA workflows — including an open-source AI-powered test case generator that automates Jira Zephyr Scale test management using a tiered AI engine (HuggingFace → Ollama → rule-based fallback).

I believe quality engineering is an architectural discipline. The best test suites are designed with the same rigour as the systems they protect — modular, observable, and built to evolve alongside the product.

// technical skills

Tools I build quality with

☕

Languages

Java (Primary)PythonJavaScriptTypeScriptSQLShell/Bash

🌐

UI & Desktop Automation

Selenium WebDriverSelenium GridAppium AndroidPlaywrightWebdriverIOpywinautoWinAppDriverAutoItWinium

⚡

API & Backend

REST AssuredPostmanJSON/XMLContract TestingMicroservicesSwagger UIOpenAPIInsomnia

🧪

AI/ML & LLM Testing

Bias TestingDrift TestingMetamorphic TestingProperty-Based Testing

🧰

AI/ML Testing Tools

DeepchecksGreat ExpectationsGiskardHypothesisDeepEvalEvidently AIPromptfooRagasMCPHuggingFace

🔩

CI/CD & DevOps

JenkinsGitHub ActionsDockerKubernetes (AKS)Azure DevOpsGitGitHubGitLab

📐

Frameworks

TestNGJUnitCucumber BDDPytestPage Object ModelData-Driven

📊

Performance

JMeterGatlingk6

🗄️

Databases

Oracle SQLPostgreSQLPL/SQLCouchDB (NoSQL)VectorDB

☁️

Cloud

Azure (AKS Certified)AWS Gen AI Essentials

// experience

9 years of impact at scale

JUN 2021 — PRESENT

Wipro

Bank of New York (BNY)

Lead SDET — Automation Architect & AI Test Engineer

Owned end-to-end quality strategy across 3 product areas — test plans, risk assessments, and coverage targets across functional, integration, regression, and smoke layers.
Architected a scalable Java + Selenium WebDriver + TestNG framework adopted across multiple product teams, eliminating 70% of manual regression effort.
Engineered comprehensive REST Assured API automation validating 40+ endpoints including auth flows, token management, and complex nested JSON schemas.
Designed Jenkins CI/CD quality gates triggering full automation suites on every commit, reducing release verification time by 60%.
Compressed regression suite runtime from 4 hours to 45 minutes via TestNG parallel execution and selective regression strategies.
Built the Eliza AI Agent for rapid transactional data access, eliminating manual lookup bottlenecks for QA and dev teams.
Mentored 4 junior QA engineers in framework design, API testing, and CI/CD — growing team automation coverage by 35% in 6 months.

AI Test Engineer — Responsibilities

Developed automated AI/LLM testing frameworks using Python, PyTest, Promptfoo, and RAGAS to evaluate accuracy, relevance, hallucination, and response quality.
Performed RAG, agent, robustness, bias, metamorphic, and drift testing, integrating AI quality gates and regression evaluations into CI/CD pipelines.
Designed test strategies for prompt engineering and agentic workflows, covering edge cases, adversarial inputs, and multi-turn conversation flows.
Built evaluation harnesses with DeepEval, Giskard, and Evidently AI to score LLM outputs against golden datasets and business rules before production release.
Defined AI quality gates — hallucination-rate thresholds, drift detection, and adversarial robustness checks — as automated CI/CD checkpoints ahead of every release.
Partnered with data science and ML engineering teams to validate model behaviour and translate evaluation results into actionable defect reports.

MAY 2018 — MAY 2021

Cognizant

Blue Cross NC

Programming Analyst

Designed automation frameworks for microservices architectures — contract testing, service interaction validation, and distributed data flow verification.
Built and owned CI/CD quality pipelines (Jenkins + Git) embedding automated UI, API, and integration gates at every build and release stage.
Introduced AI-assisted test generation, improving functional coverage while reducing manual test design effort by 25%.
Containerised test environments with Docker for consistent, reproducible automation across dev, staging, and pre-production environments.
Applied shift-left testing practices embedded in design and sprint planning — reducing UAT defect leakage by 30%.

MAR 2017 — MAY 2018

ReDIM Group

Chennai, India

Associate Software QA Engineer

Built Selenium WebDriver (Java + TestNG) scripts for web apps and Appium scripts for native Android and iOS mobile apps.
Performed REST API testing with REST Assured and integrated automation suites into Jenkins CI/CD pipelines.
Authored Test Plans, Test Strategies, and traceability matrices; managed defect lifecycle in JIRA and HP ALM.

// notable contributions

Beyond the day-to-day

🤖

Eliza AI Agent

Developed an AI agent to provide quick access to transactional and hydration data, significantly reducing manual lookup time and improving analysis efficiency.

⚡

In-Sprint Automation

Implemented in-sprint automation strategy that received direct client appreciation for accelerating release cycles and enabling on-time delivery.

🔌

Custom MCP Server

Built a custom MCP server to automate Jira Zephyr Scale test case management, powered by a tiered AI engine (HuggingFace → Ollama → rule-based fallback).

🐚

Shell Script Automation Suite

Created Shell scripts to automate recurring operational tasks, reducing manual intervention across deployment workflows.

✨

AI-Assisted Refactoring

Applied Windsurf AI to refactor Selenium and Python scripts — improving readability, long-term stability, and reusability.

🐍

Python Testing Utilities

Developed Python utilities for data parsing, report generation, and API validation — reducing regression effort by 30–50%.

// open source & side projects

Things I've built

🧪 AITestCaseGen

Open-source Python toolkit automating Jira Zephyr Scale test case management, powered by a tiered AI engine (HuggingFace → Ollama → rule-based fallback).

PythonJira ZephyrMCPHuggingFace

View on GitHub →

🛡️ LLM-Strata

A framework for LLM security and robustness testing — evaluation, guardrails, and observability workflows for AI systems.

PythonLLM SecurityDeepEvalLangfuse

View on GitHub →

🧭 Microsoft WebWright

An autonomous browser-interaction AI agent (Google Flights example) using GPT-4o and Playwright to navigate and complete web tasks.

GPT-4oPlaywrightAI Agent

View on GitHub →

⚙️ Promptfoo CI/CD Framework

Integrates Promptfoo-based prompt/LLM evaluation into CI/CD pipelines as automated quality gates.