Michael Starpoli

Key Skills

Software

Other

Appen

Micro1

Mercor

Mindrift

OneForma

Scale AI

Toloka

Top Subject Matter

Aerospace Engineering

Mechanical Engineering

Legal Services & Contract Review

Top Data Types

Text

3D Sensor

Document

Top Task Types

Evaluation Rating

Computer Programming Coding

Prompt Response Writing SFT

Data Collection

Question Answering

RLHF

Text Generation

Text Summarization

Freelancer Overview

Aerospace Engineering SME (AI Evaluation/Training). Brings 5+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Other and Mercor. Education includes Bachelor of Science, Rutgers University (2023) and Master of Science, University of Illinois Urbana-Champaign (2023). AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

Occupational Reviewer / Engineering Evaluator

TextEvaluation Rating

Review long-form, difficult occupational and engineering problems designed to evaluate model performance on realistic professional tasks. Work includes assessing outputs against detailed criteria, identifying reasoning gaps or failure points, and ensuring evaluations are accurate, consistent, and aligned with project standards. Quality is maintained through rubric-based review, careful technical judgment, and close attention to detail.

Review long-form, difficult occupational and engineering problems designed to evaluate model performance on realistic professional tasks. Work includes assessing outputs against detailed criteria, identifying reasoning gaps or failure points, and ensuring evaluations are accurate, consistent, and aligned with project standards. Quality is maintained through rubric-based review, careful technical judgment, and close attention to detail.

2025 - Present

Engineering Expert

TextPrompt Response Writing SFT

Support engineering-focused AI evaluation work by reviewing technical content, assessing response quality, and applying domain expertise to determine correctness, clarity, and completeness. Tasks involve structured review of engineering material and following detailed project guidance to ensure consistency and high-quality outputs.

Support engineering-focused AI evaluation work by reviewing technical content, assessing response quality, and applying domain expertise to determine correctness, clarity, and completeness. Tasks involve structured review of engineering material and following detailed project guidance to ensure consistency and high-quality outputs.

2025 - Present

STEM Expert

Computer Code ProgrammingComputer Programming Coding

Contribute to long-form STEM tasks involving computational reasoning, technical problem solving, and coding-based workflows. Work includes solving complex problems, reviewing model-generated responses, and helping assess accuracy, reasoning quality, and overall performance on advanced technical tasks. Quality is maintained through careful review of logic, calculations, structure, and adherence to project guidelines.

Contribute to long-form STEM tasks involving computational reasoning, technical problem solving, and coding-based workflows. Work includes solving complex problems, reviewing model-generated responses, and helping assess accuracy, reasoning quality, and overall performance on advanced technical tasks. Quality is maintained through careful review of logic, calculations, structure, and adherence to project guidelines.

2025 - Present

Mechanical Engineering Expert (AI Model Evaluation)

MercorText

As an engineering expert with Mercor, I design mechanical engineering tasks and develop objective scoring rubrics to evaluate AI model performance. I conduct audit-style quality assurance on reviewer outputs and calibrate grading consistency across the team. I document common failure patterns and provide recommendations to improve the reliability of evaluation processes. • Crafted multi-step reasoning challenges for mechanical engineering AI evaluation. • Developed and maintained objective scoring rubrics for model assessments. • Performed structured audits and QA on completed evaluations. • Recommended enhancements to improve metric consistency and reliability.

As an engineering expert with Mercor, I design mechanical engineering tasks and develop objective scoring rubrics to evaluate AI model performance. I conduct audit-style quality assurance on reviewer outputs and calibrate grading consistency across the team. I document common failure patterns and provide recommendations to improve the reliability of evaluation processes. • Crafted multi-step reasoning challenges for mechanical engineering AI evaluation. • Developed and maintained objective scoring rubrics for model assessments. • Performed structured audits and QA on completed evaluations. • Recommended enhancements to improve metric consistency and reliability.

2025 - Present

Aerospace Engineering SME (AI Evaluation/Training)

OtherText

As a subject-matter reviewer for AI research at Sepal AI, I evaluate the technical correctness and clarity of model-generated engineering content. I author and refine aerospace-focused technical prompts, test cases, and reference solutions for model evaluation. I adhere to strict confidentiality for program-specific data and methods under NDA. • Reviewed aerospace-related texts generated by AI for accuracy. • Designed evaluation prompts and test cases specific to aerospace engineering. • Provided ratings and qualitative feedback to assess AI model performance. • Maintained documentation standards to ensure evaluative consistency.

As a subject-matter reviewer for AI research at Sepal AI, I evaluate the technical correctness and clarity of model-generated engineering content. I author and refine aerospace-focused technical prompts, test cases, and reference solutions for model evaluation. I adhere to strict confidentiality for program-specific data and methods under NDA. • Reviewed aerospace-related texts generated by AI for accuracy. • Designed evaluation prompts and test cases specific to aerospace engineering. • Provided ratings and qualitative feedback to assess AI model performance. • Maintained documentation standards to ensure evaluative consistency.

2025 - Present

Show more

Education

Work History