Erhuvwu D.

Key Skills

Software

Don't disclose

Top Subject Matter

LLM fine-tuning for energy and automotive use cases

Reinforcement learning for navigation and energy optimization

Top Data Types

Text

Audio

Top Task Types

Prompt + Response Writing (SFT)

RLHF

Freelancer Overview

Freelance AI Data Specialist — Aligner AI. Brings 8+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Don't disclose. Education includes Bachelor of Science, University of Cambridge and TensorFlow Developer Certificate, N/A (2022). AI-training focus includes data types such as Text and labeling workflows including Prompt + Response Writing (SFT) and RLHF.

Labeling Experience

Freelance AI Data Specialist — Aligner AI

TextPrompt + Response Writing (SFT)

Annotated and quality-checked thousands of prompt-response pairs for LLM fine-tuning across reasoning, code, factuality, and safety. Flagged hallucinations, unsafe completions, and rubric violations to support reliable training signals and evaluation outcomes. Authored and iterated labeling guidelines for consistent annotation across energy and automotive client projects.• Classified and scored prompt-response behaviors using project rubrics and edge-case adjudication.• Conducted calibration sessions and measured inter-annotator agreement to maintain label consistency.• Prepared dataset curation artifacts, including annotation schema and QA sampling procedures.• Supported generative AI prototypes by delivering both annotated training data and model evaluation inputs.

2023 - 2024

Student Researcher — Google Student Ambassador Program

Don't discloseTextRLHF

Conducted AI research work that included building and validating reinforcement-learning approaches and evaluating performance in simulated and benchmark settings. Contributed to AI optimization research efforts with a focus on training and assessment of model behaviors. While not explicitly described as manual labeling, the work involved producing evaluation outcomes that informed training and iteration of AI models.• Built an RL pathfinding agent (Python + ROS) and tested it in simulated and small-scale robotics environments.• Researched AI-driven energy optimization models and improved predictive grid efficiency in benchmarks.• Co-authored optimization algorithm research for dynamic energy systems for peer-reviewed submission.• Presented interdisciplinary findings to student and faculty audiences.

2017 - 2021

Education

Work History