Andra D.

Key Skills

Software

Other

Telus

Mindrift

Scale AI

Top Subject Matter

Large language model training (RLHF-style) and text data annotation for AI safety and reliability

LLM prompt engineering and evaluation/feedback for alignment using text prompts and responses

Top Data Types

Text

Document

Computer Code Programming

Top Task Types

RLHF

Prompt + Response Writing (SFT)

Bounding Box

Segmentation

Classification

Object Detection

Text Generation

Question Answering

Text Summarization

Fine-tuning

Transcription

Evaluation/Rating

Computer Programming/Coding

Data Collection

Freelancer Overview

AI Training Specialist at Stellar AI (AI training tasks, user–AI simulation, and text dataset annotation). Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Other. Education includes Master of Science, University of Portsmouth (2026) and Bachelor of Science, University of Portsmouth (2025). AI-training focus includes data types such as Text and labeling workflows including RLHF and Prompt + Response Writing (SFT).

Labeling Experience

AI Training Specialist at Stellar AI (AI training tasks, user–AI simulation, and text dataset annotation)

TextRLHF

Designed and refined AI training tasks to improve large language model reasoning and decision-making in real-world scenarios. Simulated user–AI interactions to guide learning across a broad set of situations. Structured and annotated real-world text datasets (e.g., emails, chat logs, and service interactions) to enhance contextual accuracy and reliability. • Developed task templates and feedback loops for model improvement. • Performed dataset annotation and contextual structuring for better grounding. • Evaluated training outputs to support AI safety and reliability research. • Contributed high-quality, structured task design documentation for internal research and training workflows.

2025 - Present

AI Data Contributor - Outlier AI

Text

You evaluated AI-generated responses and provided structured feedback to improve model alignment and output quality. You also engineered advanced prompts to improve LLM performance across reasoning, instruction-following, and creative tasks. You collaborated with expert teams on prompt-engineering projects supporting safer, enterprise-ready AI. • Designed and iterated prompts for targeted LLM behaviors • Performed qualitative evaluation of model outputs • Provided structured feedback to guide improvements • Worked with cross-functional teams on AI prompt projects

2024 - 2025

AI Data Contributor at Outlier AI (prompt engineering, response evaluation, and structured feedback)

OtherTextPrompt + Response Writing (SFT)

Engineered advanced prompts to improve LLM performance on reasoning, instruction-following, and creative tasks. Evaluated AI-generated responses and provided structured feedback to improve model alignment and output quality. Collaborated with expert teams on prompt-engineering work supporting safer, enterprise-ready AI. • Authored and refined prompt variants for targeted capabilities. • Reviewed model responses and generated structured critique for iteration. • Supported enterprise-aligned AI behavior through prompt and feedback cycles. • Participated in team collaboration for prompt-engineering project delivery.

2024 - 2025

Education

Work History