Data Annotator
As a Data Annotator at Sahara AI, I performed tasks to support the training and evaluation of AI models. My main duties included advanced LLM evaluation, prompt testing, jailbreak scenario testing, and output refinement. I contributed to enhancing AI model responses via detailed structured feedback.• Conducted prompt engineering and LLM evaluation tasks • Tested AI models for jailbreak and adversarial outcomes • Provided structured reviews and feedback on model outputs • Supported model refinement and accuracy improvements