QA Intern

ByteBodh; India; On-site; INR 250,000 - 450,000; Full time

Job summary

ByteBodh in India seeks a motivated QA tester to contribute to the validation of autonomous AI agents, focusing on reasoning, planning, and decision-making. You will test end-to-end multi-step workflows, document results, and support product teams.

You will analyze defects, write clear defect reports, collaborate with engineers, and develop test scenarios including edge cases and long-running tasks. Basic scripting in Python is a plus; familiarity with Jira or Asana helps.

Qualifications

• Currently pursuing or recently completed a degree in Computer Science, Information Technology, or a related technical field.
• Basic understanding of Generative AI/LLMs and their non-deterministic nature.
• Foundational knowledge of Software Quality Assurance (QA) principles and the SDLC.
• Strong analytical and critical thinking skills with exceptional attention to detail.
• Familiarity with bug-tracking tools (e.g., Jira, Asana) and writing clear defect reports.
• Basic scripting skills ( Python is a plus) for simple data analysis or test execution.
• Excellent communication and collaboration skills to work with engineers and researchers.

Responsibilities

• Execute and document test plans specifically designed to validate autonomou s AI agents' reasoning and decision-making.
• Manually and semi-automatically test end-to-end multi-step workflows orchestrated by GenAI agents across enterprise tasks.
• Identify, document, and track complex defects, especially related to agent hallucination or memory failure.
• Assist in writing and refining test scenarios, focusing on edge cases, long-running tasks, and multi-agent collaboration failures.
• Maintain clear test results, contribute to quality metrics, and provide feedback to engineering and product teams.

Skills

QA fundamentals

Analytical thinking

Bug reporting

Python basics

Communication

Education

Bachelor's degree in CS/IT or related field

Tools

Jira

Asana

Job description

• Agent Validation: Execute and document test plans specifically designed to validate the reasoning, planning, and decision-making capabilities of autonomous AI agents.
• Workflow Testing: Manually and semi‑automatically test end‑to‑end multi‑step workflows orchestrated by GenAI agents across enterprise tasks.
• Defect Analysis: Identify, meticulously document, and track complex defects, especially those related to agent hallucination, poor tool selection, or memory failure.
• Test Case Development: Assist in writing and refining test scenarios, focusing on edge cases, long‑running tasks, and multi‑agent collaboration failure points.
• Documentation & Reporting: Maintain clear test results, contribute to quality metrics, and provide timely feedback to engineering and product teams.

Requirements

• Currently pursuing or recently completed a degree in Computer Science, Information Technology, or a related technical field.
• Basic understanding of Generative AI/LLMs and their non-deterministic nature.
• Foundational knowledge of Software Quality Assurance (QA) principles and the Software Development Lifecycle (SDLC).
• Strong analytical and critical thinking skills with exceptional attention to detail.
• Familiarity with at least one bug-tracking tool (e.g., Jira, Asana) and writing clear defect reports
• Basic scripting skills ( Python is a plus ) for simple data analysis or test execution.
• Excellent communication and collaboration skills to work with engineers and researchers.