Brian C.

Key Skills

Software

Other

Top Subject Matter

Software Engineering

Linguistic dataset evaluation for speech AI

LLM evaluation for image recognition and scientific visualization understanding

Top Data Types

Image

Text

Video

Top Task Types

Tracking

Entity (NER) Classification

Evaluation/Rating

Freelancer Overview

AI Evaluator - Handshake. Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor's, University of California - Los Angeles (2026). AI-training focus includes data types such as Image and Text and labeling workflows including Evaluation, Rating, and Tracking.

Labeling Experience

AI Evaluator - Handshake

ImageTrackingEntity (NER) Classification

Analyzed and evaluated domain-specific prompts to assess large language model performance for image recognition across multiple specialized subfields. Reviewed model outputs for scientific accuracy, clarity, and depth, and delivered expert feedback to improve AI understanding of complex visualizations. Conducted independent research to support prompt development and evaluation workflows for ongoing quality improvement. • Developed prompt evaluation workflows for LLM image recognition tasks • Assessed outputs against criteria for accuracy and clarity • Provided expert review to refine model behavior and responses • Supported iterative research efforts to improve evaluation quality

2026 - Present

AI Trainer — Handshake Remote (May 2026 – Present)

OtherImage

Evaluated 200+ domain-specific prompts to assess LLM performance in image recognition tasks across five specialized subfields. Analyzed LLM outputs for scientific accuracy, clarity, and depth to support prompt development and evaluation workflows. Provided expert review and feedback to improve AI understanding of complex visualizations. • Evaluated prompt quality for image recognition • Assessed output quality using scientific criteria • Reviewed complex visualizations and recommended improvements • Supported independent research for evaluation workflow design

2026 - Present

Linguistic AI Speech Consultant — Josh Talks Remote (April 2026 – May 2026)

OtherText

Evaluated US English sentence datasets for speech AI applications to ensure alignment with native usage and intended conversational context. Reviewed sentences for naturalness, clarity, register, and contextual appropriateness, flagging items that did not match real-world spoken communication. Applied linguistic analysis to support quality control for AI speech evaluation datasets in a fast-turnaround remote engagement. • Checked dataset sentences for native conversational alignment • Flagged misaligned sentences for spoken communication • Assessed linguistic properties like register and clarity • Supported QA of speech evaluation dataset quality

2026 - 2026

Education

Work History