We are looking for a QA Engineer with a passion for ensuring the quality and reliability of AI-powered applications, especially those built using Generative AI technologies. You will play a critical role in validating AI systems, including LLMs, RAG pipelines, and backend services. Your work will help shape the safety, accuracy, and robustness of AI-driven features used by thousands (or millions) of users.
Key Responsibilities
Functional Testing
· Design, execute, and maintain test cases for APIs, backend services, and UI interfaces.
· Conduct regression, integration, and exploratory testing of AI-powered features.
· Validate RESTful APIs and end-to-end workflows in web applications.
AI/LLM-Specific Testing
· Test outputs from LLMs and GenAI pipelines for factual accuracy, coherence, tone, and safety.
· Evaluate outputs for hallucination, repetition, bias, toxicity, and other model behavior anomalies.
· Create structured test prompts and scenarios to assess the consistency and reliability of AI responses.
· Perform adversarial and edge case testing, including prompt injection and jailbreak scenarios.
Automation Testing
· Develop and maintain automation test suites using tools like Selenium, Playwright, Cypress, or PyTest.
· Automate API testing workflows using Postman, REST-assured, or similar tools.
· Integrate test automation into CI/CD pipelines for continuous validation and fast feedback loops.
Non-Functional Testing
· Conduct performance, load, and stress testing on model inference APIs and backend services.
· Measure and validate latency, throughput, and resource utilization for GenAI features.
· Test system behavior under scale and ensure failover and resilience capabilities.
Data and Model Validation
· Collaborate with data scientists to verify training data integrity and model evaluation results.
· Validate semantic search results in vector databases used in RAG (Retrieval-Augmented Generation) pipelines.
· Test chaining logic and prompt orchestration using frameworks like LangChain.
Security, Compliance, and Governance
· Perform tests to identify data privacy risks, prompt injections, and leakage of sensitive content.
· Support red-teaming efforts to proactively identify vulnerabilities in GenAI systems.
· Contribute to documentation of risk mitigation plans and compliance readiness for audits.
Required Skills & Qualifications
· Bachelor’s degree in Computer Science, Engineering, or related field.
· 3+ years of professional experience in software QA; exposure to AI/ML projects is a plus.
· Strong understanding of QA methodologies, test planning, and execution.
· Hands-on experience testing APIs, backend systems, and web applications.
· Proficiency with test automation frameworks like Selenium, Playwright, Cypress, or PyTest.
· Experience with API testing tools like Postman, REST-assured, or similar.
· Familiarity with LLMs, NLP concepts, and GenAI tools (e.g., OpenAI, Hugging Face, LangChain).
· Working knowledge of Git, CI/CD tools, and test management platforms
Bachelor's degree