AI Health Specialist—RLHF and Medical Data Annotation (MSc studies)
TextRLHF
I contributed to the improvement of Large Language Models (LLMs) through Reinforcement Learning from Human Feedback (RLHF) and medical data annotation. My work involved ensuring pharmaceutical and clinical accuracy in AI-generated medical content. I validated the reliability of medical and pharmacological data used in AI training pipelines.
• Labeled and reviewed text-based medical data to support LLM development.
• Evaluated AI outputs for clinical accuracy and relevance in healthcare settings.
• Used proprietary or academic tools to annotate pharmaceutical information.
• Applied expertise in drug-drug interactions to inform RLHF processes.
I contributed to the improvement of Large Language Models (LLMs) through Reinforcement Learning from Human Feedback (RLHF) and medical data annotation. My work involved ensuring pharmaceutical and clinical accuracy in AI-generated medical content. I validated the reliability of medical and pharmacological data used in AI training pipelines. • Labeled and reviewed text-based medical data to support LLM development. • Evaluated AI outputs for clinical accuracy and relevance in healthcare settings. • Used proprietary or academic tools to annotate pharmaceutical information. • Applied expertise in drug-drug interactions to inform RLHF processes.
2023 - Present