SDET - LLM Tester (Python)

We are seeking a skilled LLM Tester to focus on testing AI and NLP models, ensuring model accuracy, reliability, and ethical compliance. The ideal candidate will have hands-on experience with testing frameworks for LLMs, coding proficiency, and familiarity with version control and CI/CD pipelines.

Responsibilities:

• Test AI/NLP/LLM models for functionality, performance, and accuracy.
• Use frameworks and tools such as Hugging Face, TensorFlow, or OpenAI APIs for model evaluation.
• Develop, execute, and maintain test scripts in programming languages such as Python, Java, or C#.
• Utilize version control systems (e.g., Git) to manage test artifacts and collaborate with development teams.
• Evaluate model performance using metrics like BLEU, ROUGE, perplexity, etc.
• Perform adversarial testing, bias detection, and ensure ethical compliance in AI systems.
• Support automation testing using tools like Selenium or Playwright within CI/CD pipelines.