Open to opportunities

panasara nikhil

@panasaranikhil

Message

I'm an LLM post-training intern improving model alignment, reasoning, and instruction-following through SFT and RLHF.

India

Message

What I'm looking for

I'm looking to contribute to applied AI and data science work involving LLM post-training, machine learning, computer vision, NLP, model evaluation, and real-world data analysis.

At Ethara AI, I'm fine-tuning large language models through supervised fine-tuning and reinforcement learning from human feedback. I evaluate outputs, optimize prompts, and iteratively test models to improve instruction-following, reasoning quality, response consistency, and alignment with human preferences.

I've built applied machine learning projects including a multimodal garbage-segregation model combining CNN and MLP architectures, achieving 97% training accuracy and 95% validation accuracy. I also developed Voichesta, a gesture- and voice-controlled system that uses OpenCV, MediaPipe, and speech recognition for hands-free computer interaction.

My work also includes YouTube data analysis, where I cleaned data, explored subscriber and content patterns, and created visualizations of growth and engagement trends. I'm pursuing an M.S. in Data Science and bring experience across Python, SQL, deep learning, computer vision, and data analysis.

Experience

Work history, roles, and key accomplishments

Current

LLM Post Training Intern

Current

Ethara AI

Jan 2026 - Present (7 months)

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.

LLM SFT Prompt Engineering Model Evaluation Python