AI/ML Developer - LLM Fine-tuning
TextFine Tuning
Fine-tuned large language models (LLMs) using domain-specific datasets to improve conversational performance for client chatbots. The task involved preparing and curating text data, running fine-tuning experiments, and evaluating model outputs to ensure quality responses. Hugging Face libraries and tools were utilized to implement the fine-tuning workflow efficiently. • Improved chatbot accuracy by 15% through targeted LLM fine-tuning.
• Processed 10,000+ documents for data preparation and ingestion.
• Used Hugging Face and Python for fine-tuning and evaluation.
• Enhanced user satisfaction by optimizing conversational models.
Fine-tuned large language models (LLMs) using domain-specific datasets to improve conversational performance for client chatbots. The task involved preparing and curating text data, running fine-tuning experiments, and evaluating model outputs to ensure quality responses. Hugging Face libraries and tools were utilized to implement the fine-tuning workflow efficiently. • Improved chatbot accuracy by 15% through targeted LLM fine-tuning. • Processed 10,000+ documents for data preparation and ingestion. • Used Hugging Face and Python for fine-tuning and evaluation. • Enhanced user satisfaction by optimizing conversational models.
2025 - Present