Geri P.

Key Skills

Software

No software listed

Top Subject Matter

LLM response quality evaluation and prompt engineering

LLM coding task evaluation

Multimodal LLM prompt and reference content creation

Top Data Types

Text

Video

Document

Top Task Types

Prompt + Response Writing (SFT)

Freelancer Overview

AI Data Evaluation & Prompt Engineering Analyst (Project Ohm / Project Helix / Project Steel) at Handshake AI. Brings 11+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include N and A. Education includes Master of Science, New Jersey Institute of Technology (2022) and Bachelor of Science, University of Crete (2019). AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

AI Data Evaluation & Prompt Engineering Analyst (Project Steel) at Handshake AI

TextPrompt + Response Writing (SFT)

Created prompts and expert-level deliverables for multimodal AI tasks spanning creative products, math modeling, video editing, music, and native macOS applications. Produced high-quality reference materials intended to guide LLM outputs and evaluation. Focused on generating instruction-and-response content that could be used as standards for downstream assessment. • Authored task prompts for multiple creative and technical domains • Produced expert deliverables as reference answers • Supported multimodal task generation standards • Helped ensure repeatable quality targets across AI assessment workflows

2026 - Present

AI Data Evaluation & Prompt Engineering Analyst (Project Helix) at Handshake AI

Developed golden solutions and fail/pass test cases for software engineering tasks. Created reference implementations and automated evaluation criteria used to judge LLM performance on complex coding problems. Ensured the test suites supported reliable, repeatable evaluation across diverse engineering prompts. • Authored expected outputs and canonical solutions • Designed automated pass/fail criteria for coding tasks • Validated LLM outputs against structured reference behavior • Supported assessment consistency for coding benchmarks

2026 - Present

AI Data Evaluation & Prompt Engineering Analyst (Project Ohm / Project Helix / Project Steel) at Handshake AI

Text

Evaluated model-generated responses across multiple quality dimensions and compared outputs against structured criteria. Assigned preference rankings based on prompt alignment, reasoning quality, accuracy, and communication clarity. Documented evaluation decisions in a clear, structured format to ensure consistency, auditability, and repeatable assessment workflows. • Used prompt alignment and reasoning quality rubrics for scoring • Performed side-by-side comparisons of LLM outputs • Produced ranked judgments for evaluation batches • Maintained structured documentation for auditability

2026 - Present

Education

Work History