Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
Scale AI
Remotasks
Text
Audio
Document
Fine-tuningLLM fine-tuning and evaluation on Computer Science QnA dataset. Brings 2+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Hugging Face. Education includes Bachelor of Science, Birla Institute of Technology and Science Pilani Hyderabad (2026). AI-training focus includes data types such as Text and labeling workflows including Fine-tuning.
I created coding tasks in different programming languages and then helped the LLMs train
I designed and executed a fine-tuning pipeline for open-source large language models (LLMs) using a custom Computer Science QnA dataset. The process involved the preparation and structuring of over 1000 QnA pairs to train and benchmark model outputs using both human and automated metrics. Parameter-efficient techniques and quantization strategies were employed to enhance model performance and streamline the AI training process. • Designed data splits and labeling strategies to facilitate RLHF and evaluation • Labeled outputs using BLEU, ROUGE-L, and semantic similarity for thorough benchmarking • Fine-tuned an LLM using LoRA and QLoRA approaches on curated datasets • Evaluated prompting methods (zero-shot, few-shot, CoT) on labeled QnA data
Bachelor of Engineering, Computer Science
GenAI Intern
Software Engineering Intern
