Senior AI Training Specialist (RLHF, LLM Fine-tuning, Evaluation)
TextRLHF
Served as a Senior AI Training Specialist with primary responsibilities in reinforcing learning from human feedback (RLHF) for large language models. Duties included fine-tuning LLMs for logical reasoning, mathematical accuracy, and domain-specific knowledge in creative arts and technical fields. Evaluated and graded model outputs, focusing on truthfulness, helpfulness, and detection of hallucinations.
• Designed and implemented prompt engineering tasks for model assessment.
• Conducted data validation and technical evaluation using Python and SQL.
• Led red teaming initiatives to detect model vulnerabilities.
• Produced structured documentation to facilitate automated workflows.
Served as a Senior AI Training Specialist with primary responsibilities in reinforcing learning from human feedback (RLHF) for large language models. Duties included fine-tuning LLMs for logical reasoning, mathematical accuracy, and domain-specific knowledge in creative arts and technical fields. Evaluated and graded model outputs, focusing on truthfulness, helpfulness, and detection of hallucinations. • Designed and implemented prompt engineering tasks for model assessment. • Conducted data validation and technical evaluation using Python and SQL. • Led red teaming initiatives to detect model vulnerabilities. • Produced structured documentation to facilitate automated workflows.
2021 - Present