Diagnosis
AI
Reasoning
+11
Operations
Accuracy
Writing
Monitoring
Onboarding
MATCH
Training
Apache Airflow
Mathematics
English
System Design
Licensed HVAC technicians to build the diagnosis and system design scenarios frontier AI labs use to test model judgment on real trade work. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Diagnosis
Compliance
AI
+8
Reasoning
Writing
Monitoring
Onboarding
MATCH
Training
English
Code Compliance
Licensed plumbers to build the diagnosis and code compliance scenarios frontier AI labs use to test model judgment on real trade work. Remote, async, paid weekly. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Licensed electricians to build the troubleshooting and code compliance scenarios frontier AI labs use to test model judgment on real trade work. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Reasoning
AI
Accuracy
+10
Medicine
English
Monitoring
Onboarding
MATCH
Training
Clinical Reasoning
Patient Safety
Clinical Practice
Clinical Medicine
PA-C certified physician assistants to build the clinical reasoning scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Linguistics
Analysis
AI
+12
Syntax
Semantics
Accuracy
Research
Teaching
Morphology
English
Make
Monitoring
Onboarding
MATCH
Training
Linguists to build the language analysis scenarios frontier AI labs use to test model judgment on syntax, semantics, and phonology. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Literary scholars to build the close reading and interpretation scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
History
Analysis
Reasoning
+11
AI
Interpretation
Accuracy
Teaching
Research
Chronology
Monitoring
Onboarding
MATCH
Training
English
Historians to build the source analysis and historical reasoning scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Philosophy
Analysis
Reasoning
+12
AI
Teaching
Research
Ethics
Epistemology
Logic
Monitoring
Onboarding
MATCH
Training
English
Argument Analysis
Philosophers to build the argument analysis and ethical reasoning scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Geology
Geoscience
AI
+12
Observation
Interpretation
Reasoning
Accuracy
Hydrology
Geophysics
English
Monitoring
Onboarding
MATCH
Training
Research
Geologists and earth scientists to build the geoscience and climate scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Psychology
Research
AI
+8
Interpretation
Reasoning
English
Monitoring
Onboarding
MATCH
Training
Behavioral Science
Psychology researchers to build the behavioral science scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Biochemistry
Biology
AI
+12
Interpretation
Reasoning
Accuracy
Logic
Research
English
Monitoring
Onboarding
MATCH
Training
Molecular Biology
Data Interpretation
Biochemists and molecular biologists to build the mechanism level life science scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Biology
AI
Interpretation
+12
Reasoning
Mechanical Systems
Accuracy
Research
Genetics
Ecology
Microbiology
Physiology
English
Monitoring
Onboarding
MATCH
Biologists to build the life science scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Tax
Reasoning
AI
+10
Accuracy
JD
SALT
English
Monitoring
Onboarding
MATCH
Training
Tax Law
LLM Evaluation
Tax attorneys to build the tax law reasoning scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Litigation
Reasoning
AI
+12
Strategic Thinking
JD
English
Monitoring
Onboarding
MATCH
Training
Strategic Reasoning
Motion Practice
Case Strategy
Document review
Legal Reasoning
Litigators to build the motions, discovery, and procedural reasoning scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Governance
AI
Reasoning
+12
Analysis
JD
Negotiation
Mechanics
English
Monitoring
Onboarding
MATCH
Training
Legal Reasoning
Negotiation Support
Due Diligence
Corporate and M&A attorneys to build the deal, diligence, and board governance scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Payments
Insurance
AML
+12
AI
Reasoning
Strategic Thinking
Make
Investigations
Analysis
Research
English
Monitoring
Onboarding
MATCH
Training
Fraud investigators across payments, insurance, AML, and corporate cases to build the investigation scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
CFP
Planning
AI
+11
Reasoning
Insurance
Accuracy
Tax
English
Monitoring
Onboarding
MATCH
Training
Financial Planning
Insurance Coverage
CFP professionals to build the financial planning scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Video editors in Premiere, DaVinci Resolve, and After Effects to evaluate video generation and demonstrate timeline workflows for frontier AI labs. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Typography
AI
Reasoning
+12
Rendering
Composition
Consistency
Adobe Illustrator
Adobe Photoshop
Adobe InDesign
English
Monitoring
Onboarding
MATCH
Training
Image Generation
Graphic designers with brand and typography depth to rate and prompt the image generation work frontier AI labs run. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Figma
AI
Reasoning
+11
Communication
Prototyping
Make
English
Monitoring
Onboarding
MATCH
Training
Product Design
Professional Experience
UX Design
UI/UX designers to build the design evaluation and Figma workflow scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
SQL
Analytics
dbt
+12
BigQuery
Snowflake
AI
Modeling
Reasoning
Engineering
Optimization
Monitoring
Onboarding
MATCH
Training
English
Analytics engineers who live in dbt, BigQuery, and Snowflake to build the SQL scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Experimentation
Testing
AI
+12
Reasoning
Statistics
Analysis
Interpretation
Modeling
Python
Monitoring
Onboarding
MATCH
Training
Biostatistics
Causal Inference
Statisticians and experimentation experts in causal inference and A/B testing to build the scenarios frontier AI labs use to test model reasoning. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
BI and data visualization experts in Tableau, Power BI, and Looker to build the dashboard scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.
Engineering
Analysis
AI
+10
Reasoning
Accuracy
Semiconductors
Monitoring
Onboarding
MATCH
Training
English
Materials Science
Materials Engineering
Materials scientists and engineers to build the selection and failure analysis scenarios frontier AI labs use to test model judgment. AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models.