AI Test Lead

Akaasa Technologies; Illinois; Remote; USD 120,000 - 180,000; Full time

Job summary

Akaasa Technologies is seeking a hands-on AI Test Lead to drive AI-assisted quality engineering for enterprise modernization projects. You will design, build, and validate AI-driven testing solutions, lead automation migrations from Selenium to Playwright, and ensure robust UI/API/End-to-End testing across legacy and modern systems.

The role requires practical AI implementation experience, reverse engineering of applications, and strong leadership to govern testing strategy, risk-based methods,

Qualifications

• 7–10 years of hands-on QA, SDET, or automation experience.
• Hands-on experience with AI-assisted automation in real-world projects.
• Migrated Selenium to Playwright or modern frameworks using AI-assisted workflows.
• Strong legacy modernization and reverse-engineering experience.
• Ability to extract requirements and test scenarios from limited documentation.

Responsibilities

• Lead quality engineering efforts for complex modernization projects.
• Design and implement AI-driven testing solutions for web and desktop apps.
• Develop and validate automation frameworks using AI tools and agents.
• Ensure security, integrations, and operational stability during migrations.
• Evaluate AI outputs against defined acceptance criteria and establish CI/CD gates.

Skills

QA Expertise

Automation Frameworks

AI-Driven Testing

Legacy System Analysis

Requirements Extraction

Test Strategy

Tools

Playwright

Selenium

Cypress

JUnit/TestNG

API Testing Tools

Service Virtualization

Job description

AI Test Lead

Location: Remote (Candidate must be in EST or CST)
Duration: 6+ Months
Interview: 2 Round Virtual

Important Note:

• LinkedIn with location before 2022
• Candidate must be in EST or CST
• Candidates who demonstrate only theoretical AI knowledge, general chatbot usage, or predominantly manual, UI-driven analysis without practical AI/agentic implementation experience will not meet the core requirements of this role.
• The successful candidate must be a hands-on technical leader who can independently design, build, and validate AI-driven quality engineering solutions for complex enterprise modernization initiatives.

Role Overview

We are seeking a hands-on AI Test Lead / Senior AI Quality Engineer with strong expertise in test automation, AI-assisted quality engineering, agentic workflows, and legacy application modernization.

The ideal candidate must have practical experience using AI tools and agents to reverse-engineer legacy applications, extract requirements from systems with limited or no documentation, generate test scenarios, and build executable automation frameworks. This role requires more than conceptual knowledge of AI or familiarity with LLMs; candidates must demonstrate the ability to independently implement AI-driven testing solutions in real-world enterprise environments.

The candidate will lead quality engineering efforts to ensure that application modernization and technology migrations preserve functional behavior, system integrations, security, and operational stability.

Required Qualifications

• 7 10 years of experience in QA, SDET, Quality Engineering, or Test Automation, including significant hands-on automation experience.
• Demonstrated hands-on experience implementing AI-assisted and agentic test automation solutions in real-world projects.
• Proven experience building test automation frameworks using AI tools and agents, rather than simply using AI chat interfaces for guidance or code suggestions.
• Practical experience migrating existing Selenium automation suites to Playwright or equivalent modern automation frameworks, preferably using AI-assisted migration workflows.
• Strong experience with legacy application modernization, reverse engineering, and test strategy development for systems with incomplete or outdated documentation.
• Ability to extract application requirements, business rules, and test scenarios through systematic analysis of application behavior, source code, APIs, logs, databases, and other available artifacts.
• Hands-on experience with AI platforms and tools such as Claude models, AWS Bedrock, or equivalent LLM-based solutions, including selecting suitable models and integrating them into practical workflows.
• Experience developing AI-driven testing solutions for web applications, with the ability to design appropriate approaches for desktop applications and other legacy technologies.
• Strong expertise in UI, API, end-to-end, regression, and system integration testing.
• Proficiency in Playwright, Selenium, Cypress, REST/API automation, or equivalent tools.
• Working knowledge of Java and/or .NET applications, SQL/databases, middleware, APIs, and enterprise integration patterns.
• Understanding of authentication and authorization mechanisms, including LDAP, Okta, tokens, and role-based access controls.
• Strong knowledge of risk-based testing, test design, defect management, root-cause analysis, and CI/CD quality gates.
• Ability to evaluate AI-generated outputs using defined acceptance criteria, repeatable validation, and human review where necessary.
• Excellent analytical and problem-solving skills, with the ability to independently design and implement solutions for complex technical challenges.

Technical Skills

• Experience with Jira, Xray, or comparable enterprise test-management tools.
• Experience with JUnit, TestNG, contract testing, and service virtualization.
• Familiarity with LLM evaluation, observability, prompt engineering, context management, and AI agent performance assessment.
• Experience testing desktop applications and legacy on-premises systems.
• Experience with performance, resilience, compatibility, and security testing during technology modernization.
• Experience in regulated industries, with an emphasis on audit-ready evidence, traceability, and quality governance.

Critical Evaluation Criteria

Candidates must be able to demonstrate practical implementation experience in the following areas:

1. AI-Assisted Automation Migration: Explain and demonstrate how AI tools were used to migrate an existing Selenium suite to Playwright, including the models, workflow, code validation, and execution results.
2. Legacy Application Reverse Engineering: Describe how requirements, business rules, and regression scenarios were extracted from undocumented or poorly documented applications.
3. Agentic Test Engineering: Demonstrate how AI agents were designed to analyze applications, generate test scenarios, develop automation scripts, and validate coverage.
4. AI-Based Framework Development: Provide examples of building a test automation framework using AI or agentic workflows, including the architecture, tools, implementation, and measurable outcomes.
5. Web and Desktop Testing: Explain how the testing approach changes between web-based and desktop applications and demonstrate the ability to identify and implement appropriate solutions.
6. Hands-On Tool Proficiency: Clearly articulate which AI models, automation tools, frameworks, and supporting technologies were used and how they were applied in actual project implementations.