For employers

Hire this AI Trainer

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

Invite to Job
J
Jordan Y.

Jordan Y.

AI Model Evaluation Contractor | CS & Math Student at RPI

USA flagNew York, Usa

Key Skills

Software

Don't disclose

Top Subject Matter

Multimodal AI model evaluation (text, image, audio, video, and software codebase prompts)
Software Engineering & Developer Tools
Mathematics & Quantitative Reasoning

Top Data Types

TextText
ImageImage
DocumentDocument

Top Task Types

No task types listed

Freelancer Overview

RPI Computer Science and Mathematics student (B.S. expected May 2027) and current AI Model Evaluation Contractor at Handshake AI since March 2026. Delivers 20+ multimodal evaluation tasks per week across text, image, audio, video, and software-codebase prompts — scoring accuracy, reasoning, and instruction-following against project rubrics, authoring detailed written feedback, and labeling/categorizing multimodal data. RCOS Project Lead of a 5-person open-source team shipping a cross-platform Rust security CLI (326 commits, 154 PRs, 174 automated tests, 6-platform CI). AWS Certified Cloud Practitioner (issued Jul 2023, valid through Jul 2026).

Labeling Experience

Project Escher

ImageImageRed TeamingRed Teaming

Author unambiguous adversarial image-based prompts designed to identify where vision-language models fail. Source reference images, construct prompts with precise ground-truth expectations, and iteratively refine wording to remove ambiguity while preserving the failure-inducing edge case. Evaluate model responses against the authored ground truth and document failure modes for downstream model training.

2026 - Present

Project Hedgehog — Multimodal AI Evaluation

Don't discloseTextTextEvaluation/RatingEvaluation/Rating

Evaluate and compare AI-generated outputs across Project Hedgehog's multimodal tracks spanning text, image, audio, and video prompts. Score model responses on accuracy, reasoning quality, and instruction-following against project rubrics. Author detailed written feedback, rationale notes, and edge-case prompts that identify model failure modes and feed directly into model improvement loops. Deliver 20+ tasks per week while maintaining consistent quality-review pass rates and adapting to evolving annotation guidelines.

2026 - Present

Project Helix — Software Codebase Analysis & Refinement

Computer Code ProgrammingComputer Code ProgrammingComputer Programming/CodingComputer Programming/Coding

Analyze complex software codebases to evaluate AI-generated code suggestions and refactors. Assess correctness, idiomatic usage, security implications, and adherence to project conventions. Provide structured written feedback that surfaces model failure modes on real-world code patterns to improve AI code-generation quality.

2026 - 2026

Education

R

Rensselaer Polytechnic Institute

Bachelor of Science, Computer Science and Mathematics

Bachelor of Science
2023 - 2027
A

Amazon Web Services

AWS Certified Cloud Practitioner, Cloud Computing

AWS Certified Cloud Practitioner
2023 - 2026

Work History

H

Handshake AI

AI Model Evaluation Contractor

Troy
2026 - Present
G

Golden Touch Home Health Care

Data Entry Assistant

Troy
2023 - 2023