AI Training Specialist (Projects: Kubrick & Hedgehog) | Handshake AI
TextRLHF
As an AI Training Specialist at Handshake AI, I executed extensive data annotation and model evaluation to support advanced machine learning workflows. I ranked and evaluated AI-generated responses, provided feedback for RLHF fine-tuning, and stress-tested LLMs with complex prompts. My work contributed to building high-quality training datasets and improving AI model robustness. • Conducted weekly evaluation of ~100 AI-generated responses for accuracy and safety.
• Annotated responses to optimize fine-tuning datasets for large language models (LLMs).
• Engineered stress-test scenarios to uncover output vulnerabilities.
• Ensured all labeling and evaluation adhered to rigorous standards and guidelines.
As an AI Training Specialist at Handshake AI, I executed extensive data annotation and model evaluation to support advanced machine learning workflows. I ranked and evaluated AI-generated responses, provided feedback for RLHF fine-tuning, and stress-tested LLMs with complex prompts. My work contributed to building high-quality training datasets and improving AI model robustness. • Conducted weekly evaluation of ~100 AI-generated responses for accuracy and safety. • Annotated responses to optimize fine-tuning datasets for large language models (LLMs). • Engineered stress-test scenarios to uncover output vulnerabilities. • Ensured all labeling and evaluation adhered to rigorous standards and guidelines.
2026 - Present