Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
Labelbox
Text
Computer Programming/Coding
RLHF
Prompt + Response Writing (SFT)
Fine-tuningI bring hands-on experience in AI training, data annotation, and LLM evaluation through remote roles focused on improving the quality, reasoning, and reliability of AI-generated outputs. My work has involved evaluating and refining Large Language Model (LLM) responses using structured rubrics, prompt engineering, RLHF methodologies, and A/B testing workflows in English-language environments. I have worked extensively with text and code-based data, helping improve AI-generated Python code through debugging, response optimization, and iterative feedback loops. Additionally, I have experience refining YAML-based agent logic, assessing model coherence and accuracy, and supporting alignment between model outputs and human intent. What sets me apart is my combination of AI training experience and strong technical foundations in Machine Learning, Python, and data analysis as a final-year Systems and Computing Engineering student. Beyond AI evaluation work, I have developed machine learning pipelines, RAG-based applications, and cloud-based analytics projects using technologies such as Python, TensorFlow, Scikit-learn, Docker, and Microsoft Azure. My background in mathematics teaching has also strengthened my analytical thinking, communication skills, and ability to apply structured problem-solving approaches when evaluating AI outputs and improving model performance.
Computer Code ProgrammingComputer Programming/CodingPrompt + Response Writing (SFT)Used Prompt Engineering, Data Annotation, A/B testing, Python, and Docker to support the improvement of AI models' performance.
TextRLHFProvided AI Trainer work focused on improving LLM and ML output quality using prompt engineering and data annotation. Used iterative feedback loops to refine model behavior and performance. Conducted A/B testing to compare prompt variants and improve response reliability. • Improved model performance via prompt engineering • Performed data annotation and iterative feedback loops • Used debugging to fix generated code errors • Optimized prompts using A/B testing
LabelboxTextPerformed LLM alignment and evaluation using structured prompt-engineering and benchmark testing. Refined YAML-based agent logic to improve alignment with human intent. Assessed output accuracy, coherence, and relevance in English using evaluation rubrics and A/B testing. • Refined YAML-based agent logic for alignment • Benchmarked LLM performance via A/B and A/B/N testing • Applied evaluation rubrics to score outputs • Improved reasoning quality and response consistency using ML principles
TextFine-tuningCompleted an end-to-end machine learning pipeline internship that included model evaluation and performance optimization. Built and trained ML and deep learning models using standard frameworks while performing data preprocessing and feature engineering. Analyzed results with statistical and data-visualization techniques and communicated findings in English. • Developed ML pipelines using CRISP-DM including evaluation • Trained models with Scikit-learn, TensorFlow, and Keras • Performed data analysis and visualization with Pandas/NumPy/Matplotlib/Seaborn • Tuned hyperparameters to improve accuracy and robustness
Bachelor of Engineering, Computer and Systems Engineering
Professional Certificate in Information Security Management, Information Security Management
AI Trainer
Freelance Math Teacher
