For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
A

Abdul Waheed

RLHF/SFT Data Labeling Contributor – Google Gemini (GAIA) Project

USA flagLahore, Usa
Intermediate

Key Skills

Software

No software listed

Top Subject Matter

Multi-modal Large Language Models (LLMs)
Generative AI
Large Language Model (LLM) Evaluation and Red-Teaming

Top Data Types

TextText
ImageImage
DocumentDocument

Top Task Types

RLHF
Fine Tuning

Freelancer Overview

RLHF/SFT Data Labeling Contributor – Google Gemini (GAIA) Project. Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Science, COMSATS University Islamabad (2023). AI-training focus includes data types such as Text and labeling workflows including RLHF, Evaluation, and Rating.

Intermediate

Labeling Experience

LLM Evaluator & Red Team Prompt Contributor – Twitter AI (X)

Text
Contributed to Twitter AI (X) by crafting adversarial prompts, performing model evaluations, and suggesting completions to enhance LLM robustness. Conducted systematic adversarial and edge-case testing to reduce hallucinations and improve model alignment. Provided qualitative and quantitative ratings on model-generated outputs. • Wrote complex, domain-specific evaluation prompts for red-teaming purposes. • Performed rating of LLM outputs against specified guidelines. • Identified and documented common model failures and edge cases. • Advised on model alignment improvements for future data labeling cycles.

Contributed to Twitter AI (X) by crafting adversarial prompts, performing model evaluations, and suggesting completions to enhance LLM robustness. Conducted systematic adversarial and edge-case testing to reduce hallucinations and improve model alignment. Provided qualitative and quantitative ratings on model-generated outputs. • Wrote complex, domain-specific evaluation prompts for red-teaming purposes. • Performed rating of LLM outputs against specified guidelines. • Identified and documented common model failures and edge cases. • Advised on model alignment improvements for future data labeling cycles.

2024 - 2025

RLHF/SFT Data Labeling Contributor – Google Gemini (GAIA) Project

TextRLHF
Led dataset creation initiatives for Google Gemini (GAIA) RLHF/SFT pipelines aimed at improving multi-modal LLM performance. Generated and curated large-scale datasets covering web, image, video, and audio modalities for fine-tuning tasks. Performed data validation and ensured dataset diversity and quality throughout the annotation cycle. • Created tailored prompts and responses for language models as part of RLHF workflows. • Coordinated data curation activities and annotated sample data for QA. • Collaborated with AI researchers to meet accuracy benchmarks during labeling. • Supported model fine-tuning by providing data/labeling process feedback.

Led dataset creation initiatives for Google Gemini (GAIA) RLHF/SFT pipelines aimed at improving multi-modal LLM performance. Generated and curated large-scale datasets covering web, image, video, and audio modalities for fine-tuning tasks. Performed data validation and ensured dataset diversity and quality throughout the annotation cycle. • Created tailored prompts and responses for language models as part of RLHF workflows. • Coordinated data curation activities and annotated sample data for QA. • Collaborated with AI researchers to meet accuracy benchmarks during labeling. • Supported model fine-tuning by providing data/labeling process feedback.

2024 - 2025

Data Labeling/Annotation Lead – transformer NLP fine-tuning projects

TextFine Tuning
Fine-tuned transformer-based NLP models on curated datasets for supervised learning tasks. Led data preparation and annotation cycles, including text cleaning, normalization, and QA for text summarization, fake news detection, and content moderation. Deployed fine-tuned models for production with continuous improvements derived from annotation feedback. • Directed data labeling efforts for the XLM-RoBERTa Tweet Classifier project. • Performed dataset QC and sample annotation for Pegasus/SAMSum and Fake News Detection models. • Designed entity and classification labels for supervised learning tasks. • Coordinated with junior staff on annotation best practices and data versioning.

Fine-tuned transformer-based NLP models on curated datasets for supervised learning tasks. Led data preparation and annotation cycles, including text cleaning, normalization, and QA for text summarization, fake news detection, and content moderation. Deployed fine-tuned models for production with continuous improvements derived from annotation feedback. • Directed data labeling efforts for the XLM-RoBERTa Tweet Classifier project. • Performed dataset QC and sample annotation for Pegasus/SAMSum and Fake News Detection models. • Designed entity and classification labels for supervised learning tasks. • Coordinated with junior staff on annotation best practices and data versioning.

2023 - 2024

Education

C

COMSATS University Islamabad

Bachelor of Science, Computer Science

Bachelor of Science
2019 - 2023

Work History

H

Hoplon InfoSec

AI Engineer

Lahore
2025 - Present
H

Hubble42 Inc.

AI/ML Engineer – Generative AI

Lahore
2024 - 2025