Aim M

Key Skills

Software

Other

Kili Technology

Top Subject Matter

AI Model Evaluation

Rlhf Domain Expertise

Multi-Modal Tasks

Top Data Types

Text

Video

Image

Top Task Types

Bounding Box

Classification

RLHF

Evaluation/Rating

Transcription

Data Collection

Object Detection

Entity (NER) Classification

Text Generation

Point/Key Point

Question Answering

Polygon

Freelancer Overview

AI Evaluation Specialist — Fellowship | Handshake AI (Multimango Platform). Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other and Kili Technology. Education includes Bachelor of Science, George Mason University (2024). AI-training focus includes data types such as Text, Video, and Geospatial and labeling workflows including Evaluation, Rating, and Bounding Box.

Labeling Experience

AI Evaluation Specialist — Fellowship | Handshake AI (Multimango Platform)

OtherText

As an AI Evaluation Specialist at Handshake AI (Multimango Platform), I performed comparative preference ranking and rubric-based model evaluation across text, image, audio, and video modalities. I assessed the quality, instruction following, and coherence of AI responses, as well as the alignment of text-to-image and text-to-video generations. I utilized structured rubrics and ELO/H2H frameworks to ensure consistent and accurate judgment across diverse tasks. • Performed side-by-side comparative evaluation of AI model outputs. • Executed preference-ranking for conversational AI and multi-modal tasks. • Applied ELO-based and H2H comparative frameworks, including Omni Elo. • Handled ambiguous multi-modal edge cases and escalated them for review.

As an AI Evaluation Specialist at Handshake AI (Multimango Platform), I performed comparative preference ranking and rubric-based model evaluation across text, image, audio, and video modalities. I assessed the quality, instruction following, and coherence of AI responses, as well as the alignment of text-to-image and text-to-video generations. I utilized structured rubrics and ELO/H2H frameworks to ensure consistent and accurate judgment across diverse tasks. • Performed side-by-side comparative evaluation of AI model outputs. • Executed preference-ranking for conversational AI and multi-modal tasks. • Applied ELO-based and H2H comparative frameworks, including Omni Elo. • Handled ambiguous multi-modal edge cases and escalated them for review.

2024 - Present

Multi-Modal AI Preference Evaluator | Prolific (Alphabet / Google AI Models)

OtherVideo

As a Multi-Modal AI Preference Evaluator at Prolific (Alphabet/Google AI Models), I completed evaluation tasks for video, image, and audio model outputs within large-scale training pipelines. I meticulously assessed outputs using task-specific rubrics, focusing on aspects such as visual quality, prompt adherence, and synchronization. I consistently delivered calibrated preference judgments despite dynamic and shifting task requirements. • Conducted evaluation of AI-generated video, image, and audio content. • Applied distinct quality criteria for each assignment and modality. • Maintained consistency in preference judgments across tasks. • Supported production model training pipelines for Alphabet/Google AI projects.

As a Multi-Modal AI Preference Evaluator at Prolific (Alphabet/Google AI Models), I completed evaluation tasks for video, image, and audio model outputs within large-scale training pipelines. I meticulously assessed outputs using task-specific rubrics, focusing on aspects such as visual quality, prompt adherence, and synchronization. I consistently delivered calibrated preference judgments despite dynamic and shifting task requirements. • Conducted evaluation of AI-generated video, image, and audio content. • Applied distinct quality criteria for each assignment and modality. • Maintained consistency in preference judgments across tasks. • Supported production model training pipelines for Alphabet/Google AI projects.

2023 - Present

Geospatial Data Annotator | Kili Technology (via Contractor)

Kili TechnologyBounding Box

As a Geospatial Data Annotator for Kili Technology, I annotated aerial satellite imagery to support computer vision model training. My tasks included applying bounding boxes and object classification workflows to label vehicles, civilian infrastructure, and geographic features. I ensured high-precision localization on complex imagery, following rigorous annotation quality standards. • Used Kili Technology platform for satellite imagery annotation. • Labeled and classified objects including infrastructure and vehicles. • Managed overlapping and occluded targets in aerial datasets. • Maintained strict adherence to quality and consistency standards.

As a Geospatial Data Annotator for Kili Technology, I annotated aerial satellite imagery to support computer vision model training. My tasks included applying bounding boxes and object classification workflows to label vehicles, civilian infrastructure, and geographic features. I ensured high-precision localization on complex imagery, following rigorous annotation quality standards. • Used Kili Technology platform for satellite imagery annotation. • Labeled and classified objects including infrastructure and vehicles. • Managed overlapping and occluded targets in aerial datasets. • Maintained strict adherence to quality and consistency standards.

2024 - 2024

Education

Work History