Delivery Data Scientist I, Turing Global India Pvt Ltd
TextFine Tuning
Refined Supervised Fine-Tuning (SFT) datasets for the Apple project, ensuring greater alignment and conversational quality for AI models. Executed Reinforcement Learning from Human Feedback (RLHF) workflows for Google’s AI models to enhance model accuracy and reliability. Led data evaluation and rework strategy for ServiceNow integrations, reducing hallucinations and streamlining workflows. • Curated and annotated text data for SFT and RLHF tasks. • Coordinated evaluation and feedback collection from a multi-disciplinary team. • Contributed to data pipeline improvements and process documentation. • Provided high-quality labeled data to support successful deployment of fine-tuned models.
Refined Supervised Fine-Tuning (SFT) datasets for the Apple project, ensuring greater alignment and conversational quality for AI models. Executed Reinforcement Learning from Human Feedback (RLHF) workflows for Google’s AI models to enhance model accuracy and reliability. Led data evaluation and rework strategy for ServiceNow integrations, reducing hallucinations and streamlining workflows. • Curated and annotated text data for SFT and RLHF tasks. • Coordinated evaluation and feedback collection from a multi-disciplinary team. • Contributed to data pipeline improvements and process documentation. • Provided high-quality labeled data to support successful deployment of fine-tuned models.
2025 - Present