Panasara Nikhil

Fine-tuned Large Language Models using Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF). Evaluated model outputs to improve instruction-following, reasoning quality, and response consistency. Optimized prompts and conducted iterative testing to improve model alignment with human preferences.

LLM Post Training Intern - Ethara AI - Remote

(2026-01)

• Fine-tuned Large Language Models using Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF).
• Evaluated model outputs to improve instruction-following, reasoning quality, and response consistency.
• Optimized prompts and conducted iterative testing to improve model alignment with human preferences.
• Worked on real-world LLM post-training workflows and quality evaluation processes.

M.S. - Data Science - Vellore Institute of Technology (2024 - 2026)

B.Sc. - Information Technology - Charotar University of Science and Technology (2021 - 2024)