Rakib T.

Key Skills

Software

Data Annotation Tech

Scale AI

Clickworker

Anno-Mage

Top Subject Matter

Large Language Model (LLM) fine-tuning and instruction dataset creation

Top Data Types

Text

Image

Audio

Top Task Types

Fine-tuning

Data Collection

Transcription

Question Answering

Classification

Freelancer Overview

Self Project / AI Training (AI Training Specialist). Brings 1+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Hugging Face Transformers. Education includes Bachelor of Technology, ABC Institute of Technology (2023) and AI Engineer Professional Certificate, Good (2025). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Fine-tuning.

Labeling Experience

Self Project / AI Training (AI Training Specialist)

Fine-tuning

Conducted AI training by fine-tuning open-source large language models on custom datasets for improved instruction following and chatbot quality. Applied QLoRA and LoRA to perform parameter-efficient supervised fine-tuning and preference optimization. Evaluated outputs using both automated benchmarks and human judgment to refine model behavior. • Fine-tuned Llama-3 8B and Mistral-7B using QLoRA/LoRA • Performed SFT and Direct Preference Optimization (DPO) • Built domain-specific multilingual chatbots (Hindi + English) • Created and validated high-quality instruction datasets using MT-Bench and human evaluation

2026 - Present

Education

Work History