Richard Bonar

Key Skills

Software

Scale AI

Remotasks

Top Subject Matter

AI Evaluation

Scenario Writing

Infrastructure Automation

Top Data Types

Text

Top Task Types

Text Generation

RLHF

Evaluation/Rating

Prompt + Response Writing (SFT)

Freelancer Overview

AI Evaluation Scenario Writer & Technical Evaluator. Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Remotasks, Internal, and Proprietary Tooling. Education includes Doctor of Philosophy, University of Lincoln (2022). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

Freelance AI Trainer / LLM Evaluator (Math and Physics)

Scale AITextText GenerationRLHF

Rubric-based evaluation and training data creation for math and physics LLM tasks. Rated model/agent outputs for correctness, completeness, instruction-following, safety, and clarity, and documented scoring rationale. Wrote and audited step-by-step solutions with correct notation and unit/dimensional checks. Produced corrected answers with concise explanations, tagged items with topic/difficulty/reasoning/error metadata, and flagged edge cases or ambiguous items to improve scoring reliability.

Rubric-based evaluation and training data creation for math and physics LLM tasks. Rated model/agent outputs for correctness, completeness, instruction-following, safety, and clarity, and documented scoring rationale. Wrote and audited step-by-step solutions with correct notation and unit/dimensional checks. Produced corrected answers with concise explanations, tagged items with topic/difficulty/reasoning/error metadata, and flagged edge cases or ambiguous items to improve scoring reliability.

2023 - 2025

Independent Research Projects: AI Tutoring Dataset Labeler

Text

Independently developed and labeled datasets for applied mathematics and physics AI evaluation tasks. Authored step-by-step solution explanations and error analyses tailored for AI training and assessment. Used Python for computation validation and ensured all documentation met reproducibility standards. • Designed and labeled advanced math and physics scenario walkthroughs replicating AI tutoring prompts. • Focused on rubric creation and systematic grading method development for LLM-style evaluation. • Conducted validation using real error cases and unit consistency checks. • Worked independently with open-source and proprietary toolchains for annotation and validation.

Independently developed and labeled datasets for applied mathematics and physics AI evaluation tasks. Authored step-by-step solution explanations and error analyses tailored for AI training and assessment. Used Python for computation validation and ensured all documentation met reproducibility standards. • Designed and labeled advanced math and physics scenario walkthroughs replicating AI tutoring prompts. • Focused on rubric creation and systematic grading method development for LLM-style evaluation. • Conducted validation using real error cases and unit consistency checks. • Worked independently with open-source and proprietary toolchains for annotation and validation.

2019 - 2023

Scientific Computing & Simulation Specialist (AI SFT/Evaluation Tasks)

TextPrompt Response Writing SFT

Designed structured prompt-response scenarios to train AI models in finance, risk analytics, and time series forecasting. Authored reproducible workflows, generated verified outputs, and documented robust ground truths for SFT-style AI training. Ensured compliance with scenario constraints and annotation standards for reproducibility and transparency. • Built and verified prompt sets for financial planning and analytics use cases. • Used Python, statsmodels, and SaaS integrations in workflow labeling. • Validated all data flows, mapping, and documentation against scenario objectives. • Coordinated labeling iterations based on agent failure modes and solution audits.

Designed structured prompt-response scenarios to train AI models in finance, risk analytics, and time series forecasting. Authored reproducible workflows, generated verified outputs, and documented robust ground truths for SFT-style AI training. Ensured compliance with scenario constraints and annotation standards for reproducibility and transparency. • Built and verified prompt sets for financial planning and analytics use cases. • Used Python, statsmodels, and SaaS integrations in workflow labeling. • Validated all data flows, mapping, and documentation against scenario objectives. • Coordinated labeling iterations based on agent failure modes and solution audits.

2021 - 2022

Education

Work History