Lakshay Chhabra

Key Skills

Software

Don't disclose

Top Subject Matter

Large Language Models (LLMs)

AI Agent Evaluation

Prompt Engineering

Top Data Types

Text

Image

Computer Code Programming

Top Task Types

Fine-tuning

Classification

Object Detection

RLHF

Evaluation/Rating

Data Collection

Prompt + Response Writing (SFT)

Text Generation

Segmentation

Freelancer Overview

I have hands-on experience in data labeling and AI training data development, with a strong focus on improving large language model (LLM) performance through Supervised Fine-Tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF). I have created high-quality annotated datasets that enhance model accuracy, coherence, and alignment with user intent. My work includes designing and evaluating AI agent trajectories to optimize decision-making processes and task completion, ensuring models behave reliably across diverse scenarios. In addition to data annotation, I bring technical expertise in building and managing Docker-based environments for reproducible testing and deployment. I have tested and analyzed GitHub repositories to validate model behavior and integration workflows, and I consistently improve model outputs by refining prompts, feedback loops, and overall training data quality. This combination of annotation precision, technical infrastructure skills, and iterative optimization allows me to contribute effectively to end-to-end AI model development and evaluation.

Labeling Experience

Education

Work History