1. Key Responsibilities

• Test Planning & Design: Analyze business requirements and Acceptance Criteria to formulate strategic Test Plans and draft comprehensive Test Cases for each software module; define testing scopes, prepare mock datasets, and configure test environments. 

• Functional Testing (Manual): Execute end-to-end functional testing for core platform components (such as 360 Customer Profiles, analytical dashboards, AI Sales assistant utilities, and post-contract tracking features); thoroughly validate User Interfaces (UI) and operational business workflows. 

• Integration & API Testing: Perform structural API testing utilizing Postman (verifying input parameters, boundary values, error response codes, and security permissions); test external system integrations (e.g., FPT Chat, SharePoint) and validate end-to-end data integrity across system boundaries. 

• Data Verification: Utilize SQL queries to validate the accuracy, consistency, and completeness of data migrated from legacy CRM platforms, as well as data programmatically generated by system pipelines (such as text extraction and vector embedding generation); perform data reconciliation against analytical dashboards. 

• AI Quality Assurance (Mandatory): 

• Curate testing golden datasets and establish evaluation benchmarks for AI/LLM text generation outputs (focusing on accuracy, completeness, proper source attribution, and hallucination containment). 

• Score, benchmark, and compare AI-generated responses across varying system prompt versions or different foundational models. 

• Identify, classify, and document unique AI regression anomalies (hallucinations, information gaps, missing source tags) and retest once engineering adjustments are deployed. 

• Regression & Automation Testing: Run systematic regression testing sweeps prior to each production product release. Assist in developing and maintaining automated test scripts (Selenium/Playwright/Cypress) for critical business paths, aiming for continuous integration into CI pipelines. 

• Defect Management & Reporting: Document software bugs with high granularity (clear steps to reproduce, severity classification, logs, and visual evidence) inside Jira. Monitor the entire bug lifecycle, conduct verification testing on developer fixes, and deliver concise Sprint quality evaluation reports. 

2. Job Requirements

Education & Experience: 

• Bachelor’s degree in computer science, Information Technology, or closely related technical disciplines. 

• 2+ years of professional software testing experience spanning manual and/or automated verification methodologies. 

Core Testing Competencies: 

• Solid grounding in software testing methodologies; proven ability to draft structured Test Plans and formal Test Cases. Proficient in functionality, system integration, and regression testing mechanics. 

• Experienced with project tracking and issue logging platforms (specifically Jira or equivalent tools). 

Technical Tooling: 

• Proficiency in running API validation protocols via Postman. 

• Strong hands-on experience writing SQL queries to examine backend databases and verify data mutations. 

• Prior exposure to or conceptual understanding of test automation frameworks (Selenium/Playwright/Cypress) is a strong plus. 

AI Output Quality Evaluation (Mandatory Requirement): 

• Possess a strong QA mindset regarding how to systematically evaluate LLM outputs against specialized quality boundaries (factuality, context recall, and hallucination prevention). 

AI-Assisted Efficiency: 

• Familiarity with leveraging next-gen AI assistants (Claude, ChatGPT…) to streamline daily workflows (e.g., accelerating test case generation, test data synthesis, or automation script scaffolding). 

Soft Skills: 

• Highly meticulous, organized, and deeply analytical. 

• Strong verbal and written communication skills; excellent critical thinking capacity to uncover system edge cases and potential failure modes. 

3. Preferred Qualifications (Nice-to-have)

• Experience with advanced test automation (integrating scripts into automated CI pipelines) or performance engineering (load/stress testing). 

• Prior experience testing AI-native architectures, large-scale language model systems, or data-heavy data warehouses. 

• Basic conceptual knowledge of RAG (Retrieval-Augmented Generation) pipelines and LLM operations to design specialized, highly effective AI testing scenarios. 

🛠️ Tech Stack Summary (For Reference) 

• Defect & Project Management: Jira. 

• API & Data Testing: Postman, SQL queries. 

• Automation Frameworks (Preferred Advantage): Selenium, Playwright, or Cypress. 

• Productivity Optimization: GenAI Assistants (Claude, ChatGPT).