AI Analyst / Prompt Engineering (Freelance)
I evaluated large language model (LLM) outputs for reasoning quality, coherence, and alignment with human expectations. I designed and tested HR-related prompts and rubrics specifically for generative AI tools. I worked on hands-on annotation, prompt writing, scenario-based AI evaluation, and other diverse AI training data tasks as part of freelancing for Toloka, Mindrift, Mercor, and others. • Evaluated AI system outputs in various domains such as text, image, audio, and video. • Generated prompts, created accurate rubrics for LLM assessment, and participated in world creation tasks for advanced AI training. • Annotated data and contributed to the alignment of generative AI behavior with human-centred design. • Ensured rigorous scenario analysis and edge-case testing of AI model performance.