AI Model Evaluation Scientist — Remote, $150–$200/hr

Synthires; United States; Remote; USD 207,000 - 276,000; Full time

Benefits offered by this job

Fully remote work

Job summary

Synthires is seeking Data Scientists and Quantitative Professionals with experience at leading organizations to support an AI research project. You’ll evaluate AI model performance across statistics, machine learning, experimentation, and quantitative reasoning to help improve model accuracy and analytical capabilities.

Fully remote work with compensation of $150–$200/hour. You will create prompts, datasets, and reference solutions, and identify flaws in methodologies and reasoning to advance

Qualifications

• 1 year of experience in technology, finance, research, or related field, with some experience in past 3 years.
• Strong understanding of Python, statistics, machine learning, and data analysis.
• Experience with Pandas, data modeling, and experimentation.
• Strong analytical and quantitative reasoning skills.
• Ability to communicate technical and statistical concepts clearly in writing.
• Based in an English-speaking country.

Responsibilities

• Evaluate AI-generated outputs involving data science, statistics, machine learning, and quantitative problems.
• Create challenging prompts, datasets, and reference solutions.
• Identify flawed methodologies, statistical errors, and weaknesses in quantitative reasoning.
• Assess data analysis, experimentation approaches, and data modeling techniques.

Skills

Python

Statistics

Machine learning

Data analysis

Pandas

Data modeling

Experimentation

Written communication

English-speaking country

Tools

Pandas

Data modeling

Job description

Synthires is seeking Data Scientists and Quantitative Professionals with experience at leading organizations to support an AI research project. You’ll evaluate AI model performance across statistics, machine learning, experimentation, and quantitative reasoning to help improve model accuracy and analytical capabilities.

Fully remote work with compensation of $150–$200/hour. You will create prompts, datasets, and reference solutions, and identify flaws in methodologies and reasoning to advance