Freelancer

Key Skills

Software

No software listed

Top Subject Matter

Generative AI / NLP (multilingual Hindi-English)

Generative AI / LLM fine-tuning (Hindi-English)

Data annotation for NLP / GenAI training (Hindi-English)

Top Data Types

Text

Document

Image

Top Task Types

Fine-tuning

Prompt + Response Writing (SFT)

Classification

Text Generation

RLHF

Transcription

Question Answering

Freelancer Overview

LLM Trainer & Evaluator (AI evaluation and model training support). Education includes Bachelor of Science, University of Delhi (2023). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Fine-tuning.

Labeling Experience

Data Annotator / LLM Data Trainer (annotation and SFT-style data prep)

Don't discloseTextPrompt + Response Writing (SFT)

Contributed to data annotation and annotation-adjacent dataset preparation for GenAI applications. Produced and refined prompts and training text to create model-ready examples for supervised fine-tuning workflows. Followed detailed guidelines to maintain accuracy, consistency, and cultural correctness across languages. • Data annotation for GenAI/NLP tasks • Prompt engineering and training example writing • Supervised fine-tuning style prompt-response preparation • Self-QA for guideline compliance and consistency

2023 - Present

LLM Trainer (AI training and fine-tuning)

Don't discloseTextFine-tuning

Performed hands-on LLM training and fine-tuning using curated text datasets and preference-based alignment concepts. Worked with RLHF and preference-based methods to support model alignment and better responses. Combined multilingual communication strength to ensure high-quality, contextually accurate training materials. • RLHF and preference-based alignment • LLM training and fine-tuning • Curated multilingual text datasets • Consistency-focused training preparation

2023 - Present

LLM Trainer & Evaluator (AI evaluation and model training support)

Don't discloseText

Trained and evaluated Large Language Models (LLMs) using prompt engineering, dataset curation, and output quality assessment. Assessed generated text for quality, bias indicators, and alignment with expected behavior. Applied AI evaluation metrics to support iterative improvements in model performance. • LLM evaluation and output quality assessment • Bias identification and evaluation • Prompt engineering and dataset curation • Quality checks for model-ready training outputs

2023 - Present

Education

Work History