Srishty Goyal

About Srishty Goyal

Providing specialized periodontal care while managing patient education, treatment…

Experience

1. Rlhf Trainer

   Soul Ai

   Aug 2025 — Present

   Bridging Human Intuition with Machine Learning | Ensuring Ethical AI BehaviorAs an RLHF Trainer, I contribute to the development of responsible and human-aligned AI systems by providing high-quality, structured feedback that guides machine learning models toward more accurate, ethical, and human-like responses.My role focuses on training AI systems using human judgment and contextual reasoning to reinforce desired behaviors in natural language processing models—ensuring they are safe, context-aware, and aligned with user expectations.Key Contributions: Evaluating and ranking model outputs based on clarity, coherence, factuality, and appropriateness Providing nuanced feedback for language models like GPT or other LLMs Collaborating with researchers to fine-tune reward models using human preference data Supporting model alignment to ethical, inclusive, and user-friendly communication standards Ensuring data quality through attention to ambiguity, bias, and prompt interpretationBy combining domain expertise, ethical sensitivity, and attention to linguistic detail, I aim to make AI not just smarter—but more human-aligned.

Education

• Manipal Academy of Higher Education

  BDS

  2014 — 2018

• KIIT - Kalinga Institute of Industrial Technology

  MDS

  2021 — 2024