AI/ML Evaluator

Job Overview 

We are seeking analytical and technically skilled AI/ML Evaluators to review and evaluate complex AI system behaviour using expert human judgment. 

In this role, you will analyse AI system outputs, system telemetry, and other relevant technical signals to evaluate patterns of behaviour. A key part of the role will involve helping distinguish legitimate user activity from sophisticated automated or bot activity based on available data and defined project guidelines. 

Your evaluations will provide high-quality, human-verified data used to train, evaluate, and improve AI systems. You will work with complex and sometimes ambiguous information, applying your understanding of AI/ML concepts and analytical reasoning to make accurate and consistent judgments. 

An ideal candidate has a strong understanding of AI and machine learning concepts and is comfortable analysing technical data and system behaviour. You should be able to identify meaningful patterns, interpret complex signals, and make informed decisions based on evidence and project requirements. 

Your work will help improve the accuracy and reliability of AI systems used to identify automated abuse while reducing the risk of incorrectly classifying legitimate user activity. 

Project Details

• Contract Type: Freelance, with the potential to convert to a full-time role.
• Pay Rate: US$72 per hour
• Location: United States
• Language: English

Responsibilities 

• Review and evaluate AI system behaviour, outputs, and relevant technical data according to defined project guidelines.  
• Analyse system telemetry, event data, signals, and other technical information to identify meaningful patterns.  
• Evaluate patterns and signals that may help distinguish legitimate user activity from automated or bot activity.  
• Apply AI/ML knowledge and expert human judgment when reviewing complex or ambiguous cases.  
• Identify unusual patterns, inconsistencies, or behaviours that may require further review.  
• Evaluate complex cases using available evidence, context, and defined project requirements.  
• Classify, label, or annotate assigned data accurately and consistently.  
• Provide high-quality human evaluations to support AI system training, evaluation, and improvement.  
• Document decisions and supporting reasoning clearly when required.  
• Identify unclear or unusual cases and flag them according to defined project processes.  
• Apply detailed project guidelines consistently across assigned tasks.  
• Maintain high levels of quality, accuracy, consistency, and attention to detail.  

Required Qualifications 

• Educational background or equivalent experience in Artificial Intelligence, Machine Learning, Computer Science, Data Science, Statistics, Engineering, or a related field.  
• Experience working with AI/ML systems, machine learning models, AI evaluation, data analysis, or technical system analysis.  
• Strong understanding of core AI and machine learning concepts.  
• Ability to analyse complex technical data, system behaviour, and patterns.  
• Experience evaluating AI systems, models, outputs, or data is preferred.  
• Familiarity with system telemetry, event data, logs, or other technical signals is preferred.  
• Strong analytical and problem-solving skills.  
• Ability to identify meaningful patterns and make informed decisions based on complex or incomplete information.  
• Strong attention to detail and the ability to apply detailed guidelines consistently.  
• Experience with data annotation, AI evaluation, human feedback, model evaluation, or structured data review is preferred.  
• Familiarity with bot detection, automated abuse detection, anomaly detection, fraud detection, or similar areas is preferred.  
• Strong written English comprehension and documentation skills.