Vandana S S

Key Skills

Software

AWS SageMaker

CVAT

Internal/Proprietary Tooling

Top Subject Matter

No subject matter listed

Top Data Types

Image

Text

Video

Top Label Types

Evaluation Rating

Fine Tuning

RLHF

Text Generation

Text Summarization

Freelancer Overview

I have specialized experience in RLHF and SFT methodologies to optimize large language models. I am skilled in providing high-quality preference data for reinforcement learning, crafting demonstrations for supervised fine-tuning, and evaluating model outputs against quality benchmarks. Additionally, I have experience identifying reasoning errors, hallucinations, and alignment issues to enhance model performance. I have demonstrated the ability to apply complex annotation guidelines across diverse content types and contribute to the development of more accurate, helpful, and ethically aligned AI systems. I am also experienced in managing complex datasets using Excel, Python, SQL, Power BI, and Tableau to generate actionable insights and support decision-making. My strength lies in the ability to become a subject matter expert in a short time frame. Additionally I hold "Hands-on-Data Annotation: Applied Machine Learning" Certification. https://www.linkedin.com/in/vandana-s-s-98196515a

Labeling Experience

Data Labeling Classification

Internal Proprietary ToolingTextPrompt Response Writing SFT

This project required labeling data in line with project specifications.

This project required labeling data in line with project specifications.

2024 - 2024

RLHF in LLMs

Internal Proprietary ToolingTextRLHF

This project dealt specifically with enhancing response quality.

This project dealt specifically with enhancing response quality.

2024 - 2024

Single Label for Image Classification of Footwear

RoboflowImageClassification

The project involved image classification of a dataset consisting of sneakers and boots.

The project involved image classification of a dataset consisting of sneakers and boots.

2024 - 2024

Object Detection of Cars and People

CVATImageBounding Box

Annotated datasets for object detection using bounding boxes. Objects annotated included cars and people.

Annotated datasets for object detection using bounding boxes. Objects annotated included cars and people.

2024 - 2024

Image Classification of Footwear

CVATImageClassification

The project involved image classification of sneakers and boots.

The project involved image classification of sneakers and boots.

2024 - 2024

Education

Work History