Nicholas Saint - AI Prompt Evaluation (Self-Directed)

Key Skills

Software

Other

Top Subject Matter

AI/Language Model Evaluation

Legal Services & Contract Review

Regulatory Compliance & Risk Analysis

Top Data Types

Text

Document

Computer Code Programming

Top Task Types

RLHF

Red Teaming

Text Summarization

Data Collection

Computer Programming/Coding

Prompt + Response Writing (SFT)

Question Answering

Text Generation

Classification

Evaluation/Rating

Function Calling

Freelancer Overview

I am a meticulous technical evaluator and data engineer with a strong foundation in complex system diagnostics and electronic integration. I have successfully translated my expertise in root-cause analysis and hardware validation into the AI training space, focusing on systematic LLM output evaluation, prompt testing, and strict adherence to rubric-based scoring for technical accuracy, instruction following, and safety constraints. My hands-on experience includes developing Python-based AI evaluation frameworks, benchmarking multi-LLM autonomous architectures, and categorizing specialized financial intent data to train custom NLP models. I excel at structured data validation, anomaly detection, and creating high-quality, technically rigorous datasets. This combination of deep systems engineering and applied AI QA ensures I deliver highly precise, edge-case-aware evaluations for complex data labeling tasks.

IntermediateEnglish

Labeling Experience

Financial Intent Data Categorization

TextFine Tuning

Labeled and categorized financial natural language queries to support the training of a custom intent-recognition model. Created a dataset of categorized transactions for model validation, ensuring high precision and data quality through iterative cross-referencing of domain-specific terminology.

2026 - Present

LLM Benchmarking & Technical Evaluation

TextFunction Calling

Conducted systematic evaluation of outputs from multiple LLMs to benchmark reasoning capabilities for an autonomous routing project. Rated model responses for logical consistency, technical accuracy, and adherence to complex system constraints. Applied strict quality measures to evaluate factual grounding across different model backends.

2026 - Present

AI Prompt Evaluation (Self-Directed)

OtherText

Evaluated AI/LLM-generated outputs for correctness, reasoning quality, and edge-case handling. Designed structured prompts and developed scoring criteria to assess language model response reliability. Documented evaluation results to improve consistency and output quality. • Analyzed AI-generated text for factuality and clarity • Developed custom prompts for specialized edge-case testing • Rated model outputs using defined rubrics • Produced reports to guide model refinement

2023 - 2023

Education

R

Rutgers University

Bachelor of Science, Electrical and Computer Engineering

Bachelor of Science

2018 - 2022

H

Housatonic Community College

Associate Degree, Engineering Science

Associate Degree

2016 - 2018

Work History

A

ASML

Electronic Integration Engineer

Wilton

2022 - Present

L

Leidos

Field Engineer

Remote

2020 - 2021