Emmanuel A.

Key Skills

Software

Other

Axiom AI

Clickworker

CloudFactory

Data Annotation Tech

iMerit

Mercor

Micro1

Top Subject Matter

AI model evaluation

prompt-based quality assurance

and conversational AI safety/alignment

Top Data Types

Audio

Text

Video

Top Task Types

Prompt + Response Writing (SFT)

Freelancer Overview

AI Evaluation Specialist (GARIUM INC). Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other and Axiom AI. Education includes Bachelor of Science, Carnegie Mellon University (2017). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

AI Automation Specialist (AXIOM)

Axiom AITextPrompt + Response Writing (SFT)

Designed and deployed AI automation workflows for clients by analyzing current operational processes for AI integration readiness. Created and used prompt sets as part of engineering and quality assurance for AI-driven solution outputs during proof-of-concepts. Followed up with leads by demonstrating prototypes, addressing technical questions, and supporting adoption of automation technologies. • Assessed client workflows against technical criteria for AI integration. • Participated in prompt set engineering and benchmarking model outputs for evaluation. • Conducted proof-of-concept demonstrations and communicated system requirements. • Coordinated next steps with solution architects or senior engineers when criteria were met.

2023 - 2025

AI Evaluation Specialist (GARIUM INC)

OtherText

Benchmarked and tested AI model outputs to assess conversational quality against strict criteria. Engineered targeted prompt sets to validate baseline thresholds for accuracy, safety, and alignment before production use or escalation. Tracked performance metrics across ongoing training cycles and provided structured feedback to refine models. • Evaluated model performance gaps and explained findings to development teams. • Reviewed edge cases and clarified failure modes for optimization. • Supported decisions to clear models for production or escalate to senior data scientists. • Measured ongoing training progress using recurring performance metrics.

2020 - 2022

Education

Work History