Viyctoriya M (m)

Skilled at analyzing AI behavior, evaluating model outputs, and providing detailed rationales to improve performance. Experienced working independently on complex AI projects while maintaining strict quality standards, and attention to detail. Passionate about emerging AI technologies and motivated by continuous learning.

AI Evaluation Specialist at Freelance (2023-02 – Present)

AI Evaluation Specialist with 4 years of experience contributing to the development and improvement of artificial intelligence systems through human evaluation, data quality, and model testing. Experienced in NLP, LLMs evaluation, RLHF, multimodal data annotation, AI transcription, and quality assurance.

• Contributed to AI development projects focused on training and improving machine learning systems and large language models.
• Evaluated AI-generated responses for accuracy, relevance, reasoning, factuality, safety, and instruction following, etc.
• Performed RLHF tasks by providing structured feedback and detailed written rationales.
• Tested and analyzed AI models through complex evaluation scenarios, identifying limitations and inconsistencies.
• Participated in confidential pre-release evaluations of advanced AI systems, providing analytical feedback to support model improvement.
• Worked with NLP datasets including text classification, language understanding, and conversational AI evaluation.
• Conducted AI transcription, audio analysis, data validation, and quality review.
• Applied complex project guidelines while maintaining high accuracy and consistency.
• Independently managed multiple AI projects requiring adaptability, research skills, and strong attention to detail.