Functional Leader - Quality Assurance

EXL; India; On-site; INR 1,100,000 - 2,000,000; Full time

Job summary

EXL is seeking a Quality Assurance (QA) Engineer specializing in Conversational AI and Agentic AI, with 3-7 years in testing, QA, and reporting. You will validate AI-driven workflows, test LLM-powered applications, and ensure safety, privacy, and performance in production environments.

Collaborate with product managers, data scientists, prompt engineers, and developers to design test strategies, execute functional, regression, and performance tests, and generate actionable quality metrics and

Qualifications

• 3-7 years of software testing and quality assurance experience in AI domains.
• Strong knowledge of QA methodologies, SDLC/STLC, and defect management.
• Experience testing Conversational AI platforms and AI-driven apps.

Responsibilities

• Develop and execute test cases for Conversational AI and Agentic AI applications.
• Perform functional, regression, integration, performance, and end-to-end testing.
• Validate AI agent decision-making, workflows, and tool integrations.
• Identify, document, and track defects using JIRA and report testing results.
• Design comprehensive test strategies for conversational flows and edge cases.

Skills

QA methodologies

SDLC/STLC

defect management

test strategy design

cross-functional collaboration

data analysis & reporting

Tools

JIRA

Postman

Swagger

Git

Job description

Job Description:

Quality Assurance (QA) Engineer – Conversational AI & Agentic AI

Job Overview

We are looking for a Quality Assurance (QA) Engineer with 3-7 years of experience in testing, QA, and reporting, specifically within the field of Conversational AI and Agentic AI systems. The ideal candidate will have a strong understanding of standard testing practices and be passionate about ensuring the highest quality standards in AI-driven applications. This role involves validating conversational experiences, AI-powered workflows, autonomous agent behaviors, integrations with external tools and APIs, and ensuring the reliability, safety, and performance of AI systems in production environments.

Key Responsibilities

1. Develop and execute test cases, scripts, and procedures for Conversational AI and Agentic AI applications.
2. Collaborate with product managers, developers, data scientists, prompt engineers, and other stakeholders to ensure quality standards are met throughout the development lifecycle.
3. Perform functional, regression, integration, performance, and end-to-end testing across conversational AI platforms and agent-based AI systems.
4. Validate AI agent decision-making, task execution, multi-step workflows, reasoning paths, and interactions with external tools, APIs, and knowledge sources.
5. Test LLM-powered applications for accuracy, relevance, consistency, hallucinations, guardrail compliance, and response quality.
6. Evaluate agent orchestration capabilities, including multi-agent collaboration, task decomposition, context management, memory retention, and tool utilization.
7. Identify, document, and track defects using JIRA and provide detailed reports on testing results.
8. Analyze requirements and design comprehensive test strategies covering conversational flows, autonomous agent behaviors, integrations, and edge-case scenarios.
9. Conduct prompt, response, and workflow validation to ensure optimal performance and user experience.
10. Perform security, privacy, bias, and responsible AI testing to validate compliance with organizational and regulatory standards.
11. Generate test reports, dashboards, and quality metrics for stakeholders, ensuring clear and actionable insights.
12. Contribute to the continuous improvement of AI testing processes, frameworks, methodologies, and automation capabilities.

Required Qualifications

1. 3-7 years of experience in software testing and quality assurance, with exposure to Conversational AI, Generative AI, Agentic AI, or similar AI technologies.
2. Strong knowledge of QA methodologies, SDLC, STLC, defect management, and validation techniques.
3. Experience testing conversational AI platforms, chatbots, voicebots, virtual assistants, or AI-driven applications.
4. Understanding of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), prompt engineering concepts, and AI agent architectures.
5. Experience with JIRA for defect tracking and project management.
6. Strong proficiency in Excel for data analysis, reporting, and test metrics.
7. Familiarity with API testing tools such as Postman, Swagger, or equivalent.
8. Experience in functional, integration, performance, security, and user acceptance testing.
9. Understanding of AI evaluation metrics, model behavior analysis, and conversational testing frameworks.
10. Ability to work effectively in cross-functional teams and adapt to fast-paced environments.
11. Strong analytical, troubleshooting, and problem-solving skills.

Desired Qualifications

1. Experience with Agentic AI frameworks such as LangGraph, CrewAI, AutoGen, Semantic Kernel, LangChain, or similar platforms.
2. Experience with automated testing tools and scripting languages (Python, JavaScript, etc.).
3. Exposure to NLP, NLU, LLM evaluation, prompt testing, and AI model validation.
4. Knowledge of cloud AI platforms such as Google CCAI/Dialogflow, Azure AI, AWS Bedrock, Amazon Lex, or OpenAI-based solutions.
5. Familiarity with version control systems (Git, GitHub, Azure DevOps).
6. Experience developing AI test automation frameworks and evaluation pipelines.
7. Understanding of Responsible AI principles, AI governance, model monitoring, and risk assessment.

Personal Attributes

1. Attention to detail and a commitment to delivering high-quality work.
2. Strong communication and stakeholder management skills, both written and verbal.
3. Self-motivated with a passion for AI innovation, quality engineering, and continuous improvement.
4. Ability to manage multiple priorities in a dynamic, fast-paced environment.
5. Curiosity to explore emerging AI technologies and evaluate complex AI agent behaviors.
6. Strong critical thinking skills with the ability to identify risks, edge-case scenarios and quality gaps in AI systems.

Preferred Experience Areas

• Conversational AI Testing (Chatbots, Voicebots, Virtual Assistants)
• Generative AI & LLM Testing
• Agentic AI Testing
• RAG Validation
• Prompt Testing and Optimization
• AI Safety & Responsible AI Testing
• API and Integration Testing
• Test Automation
• Cloud-based AI Solutions

Responsibilities

Quality Assurance (QA) Engineer – Conversational AI & Agentic AI

Job Overview

We are looking for a Quality Assurance (QA) Engineer with 3-7 years of experience in testing, QA, and reporting, specifically within the field of Conversational AI and Agentic AI systems. The ideal candidate will have a strong understanding of standard testing practices and be passionate about ensuring the highest quality standards in AI-driven applications. This role involves validating conversational experiences, AI-powered workflows, autonomous agent behaviors, integrations with external tools and APIs, and ensuring the reliability, safety, and performance of AI systems in production environments.

Key Responsibilities

1. Develop and execute test cases, scripts, and procedures for Conversational AI and Agentic AI applications.
2. Collaborate with product managers, developers, data scientists, prompt engineers, and other stakeholders to ensure quality standards are met throughout the development lifecycle.
3. Perform functional, regression, integration, performance, and end-to-end testing across conversational AI platforms and agent-based AI systems.
4. Validate AI agent decision-making, task execution, multi-step workflows, reasoning paths, and interactions with external tools, APIs, and knowledge sources.
5. Test LLM-powered applications for accuracy, relevance, consistency, hallucinations, guardrail compliance, and response quality.
6. Evaluate agent orchestration capabilities, including multi-agent collaboration, task decomposition, context management, memory retention, and tool utilization.
7. Identify, document, and track defects using JIRA and provide detailed reports on testing results.
8. Analyze requirements and design comprehensive test strategies covering conversational flows, autonomous agent behaviors, integrations, and edge-case scenarios.
9. Conduct prompt, response, and workflow validation to ensure optimal performance and user experience.
10. Perform security, privacy, bias, and responsible AI testing to validate compliance