Test Automation & Framework Development

- Design, develop, and maintain scalable web UI automation frameworks using Playwright (TypeScript / Python / JavaScript) following Page Object Model (POM) architecture
- Implement parallel execution, retry strategies, flaky test analysis, and test isolation for reliable, stable test runs
- Create and manage shared utilities — logging, test data handling, Microsoft Teams/Slack integrations, and HTML/Allure reporting
- Define coding standards, perform code reviews, and onboard team members to the automation framework

CI/CD & Pipeline Integration

- Configure and maintain GitHub Actions workflows for automated test execution — integrate with CI pipelines for reporting, failure screenshots, and alerting
- Set up Git-event-driven test triggers and post structured test result summaries to collaboration channels
- Work with shell scripting and Docker basics to support pipeline reliability and scalability

AI Agent Development & Integration

- Contribute to AI-native test automation pipelines leveraging LLM APIs (Claude API / OpenAI) — including intelligent test selection, auto test generation via Playwright Codegen, and automated defect reporting
- Build or support autonomous agent workflows with multi-step reasoning, tool use, and integration with external APIs (GitHub, Jira, REST APIs)
- Develop and refine prompt engineering strategies to build reliable, deterministic agent behavior
- Deploy and monitor AI agents via FastAPI or serverless functions; handle edge cases and output validation

Quality & Reporting

- Perform functional, regression, smoke, and end-to-end test coverage for web platforms




- Manage test data setup and teardown; generate Allure reports and share structured summaries with stakeholders
- Analyze test failures, identify root causes, and drive continuous improvement of test coverage and quality processes

Automation & Testing

- Strong proficiency in Playwright (TypeScript / Python / JavaScript) for web UI automation
- Solid understanding of Page Object Model (POM) and scalable framework design principles — must have designed frameworks, not just written scripts
- Familiarity with BDD frameworks such as Cucumber
- Experience with test runners: pytest or Playwright Test Runner
- Hands-on experience with Selenium WebDriver is a plus

Languages & Tools

- Proficient in TypeScript and/or Python; familiarity with JavaScript is a plus
- Experience with GitHub Actions and CI/CD pipeline configuration hands-on YAML writing required
- Working knowledge of Shell / Bash scripting
- Familiarity with REST API testing and integrations with tools like GitHub and Jira

AI & LLM Exposure

- Working knowledge of LLM APIs (Claude API / OpenAI) for building AI-powered automation or agent workflows
- Hands-on experience with prompt engineering for reliable, structured agent outputs
- Exposure to MCP (Model Context Protocol) or agent skill-based design patterns
- Familiarity with FastAPI for deploying lightweight agent services

Soft Skills

- Strong debugging, analytical, and problem-solving skills — must be able to diagnose failures live
- Ability to independently own modules and drive projects with minimal supervision
- Positive communication skills; ability to write structured summaries and documentation for both technical and non-technical stakeholders

Skills:- Playwright, Selenium, Fullstack Developer, cicd, TypeScript, Javascript and Large Language Models (LLM) tuning

📌 Software Development Engineer in Test (Baner)
🏢 Brownbox Consulting
📍 Baner