For employers

Hire this AI Trainer

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

Invite to Job
T
Taggart T.

Taggart T.

Independent AI safety researcher

USA flagBozeman, Usa

Key Skills

Software

No software listed

Top Subject Matter

Machine learning - safety related(jailbreaking, redteaming)
Mathematics
Python programming

Top Data Types

TextText
DocumentDocument

Top Task Types

Computer Programming/CodingComputer Programming/Coding
RLHFRLHF
Red TeamingRed Teaming
ClassificationClassification

Freelancer Overview

Apart Research AIxBio Hackathon - Pandemic Early Warning (Multi-Signal Surveillance Evaluation - Track 2). Brings 3+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Python, pandas, and DeBERTa. Education includes Bachelor of Science, Montana State University (2026). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Evaluation and Rating.

Labeling Experience

ICU mortality rate

DocumentDocumentClassificationClassification

Took in ICU data, trained various methods to classify and identify mortality rate from biometric data and written notes.

2026 - 2026

Apart Research AIxBio Hackathon - Pandemic Early Warning (Multi-Signal Surveillance Evaluation - Track 2)

Developed and submitted an evaluation paper for an AIxBio Hackathon focused on pandemic early warning using multiple surveillance signal types across the 2021–2024 endemic transition and a 2021–2025 influenza control. Assessed quantitative changes and performed detector evaluation by replicating CDC dashboard logic and testing statistical change-point methods against variant-peak ground truth. The work emphasized measurement validity, privacy-relevant aggregation implications, and rigorous replication of established pipelines. • Evaluated NWSS wastewater, Google Trends, Wikipedia pageviews, and HHS hospital admissions signals. • Analyzed novelty-cycle artifacts (e.g., variance compression) and compared against influenza controls. • Conducted LLM-based prompt surveillance sparsity analysis using a DeBERTa classifier on WildChat. • Implemented and benchmarked CUSUM/control-chart detectors using CDC variant-peak ground truth.

2026 - 2026

Education

M

Montana State University

Bachelor of Science, Mathematics

Bachelor of Science
2022 - 2026

Work History

P

Panda Express

Cook

Bozeman
2024 - Present
B

Brant Schmidt Construction

Roofing Crew Member

Bozeman
2025