LLM Fine-tuning/Data Labeling (Senior AI Engineer)
TextFine Tuning
As a Senior AI Engineer, I fine-tuned state-of-the-art Large Language Models (LLMs) for domain-specific tasks. This process involved preparing and curating text datasets, running supervised fine-tuning, and evaluating model outputs on various NLP benchmarks. My work contributed directly to improving classification accuracy by 25% for the organization's AI products.
• Led the domain adaptation of LLMs for client applications.
• Designed tailored data pipelines for robust training samples.
• Evaluated and iteratively improved LLM predictions.
• Collaborated with cross-functional teams to align labels with business goals.
As a Senior AI Engineer, I fine-tuned state-of-the-art Large Language Models (LLMs) for domain-specific tasks. This process involved preparing and curating text datasets, running supervised fine-tuning, and evaluating model outputs on various NLP benchmarks. My work contributed directly to improving classification accuracy by 25% for the organization's AI products. • Led the domain adaptation of LLMs for client applications. • Designed tailored data pipelines for robust training samples. • Evaluated and iteratively improved LLM predictions. • Collaborated with cross-functional teams to align labels with business goals.
2021 - Present