Kevin F.

Key Skills

Software

Internal/Proprietary Tooling

Top Subject Matter

Finance / Legal

Cryptocurrency

Programming (Python, Rust)

Top Data Types

Text

Document

Top Task Types

Red Teaming

Text Generation

Fine-tuning

Computer Programming/Coding

Data Collection

Evaluation/Rating

Question Answering

Freelancer Overview

LLM Evaluation and Prompt Engineering (Founder & Systems Architect, Abraxas Consulting dba Tamrael). Brings 15+ years of professional experience across finance, tech, security research, legal operations, contract review, compliance, and structured analysis. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Science, Fordham University (2011) and High School Diploma, High Technology High School (2007). AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

LLM Evaluator & AI Output Rater (Systems Architect – Abraxas Consulting)

Text

I engineered, orchestrated, and evaluated large language model (LLM) outputs to optimize AI performance. My tasks primarily included prompt engineering, LLM evaluation, and ranking of AI outputs, conducting zero-overhead coordination and iterative evaluation cycles. The experience involved deploying models on self-hosted infrastructure and ensuring model quality through systematic evaluation rounds. • Multi-model consensus and orchestration for over 1.53 billion tokens processed • Used prompt engineering and output ranking to enhance output quality and control cost • Continuous LLM output evaluation using custom coordination runtime • Leveraged Rust and Mojo to ensure sub-millisecond latency in evaluation

2025 - Present

Education

Work History