Applied research lab curating data solutions to accelerate foundation model development. Serving every frontier AI lab.
San Francisco, CA
AfterQuery is an applied research lab curating data solutions to accelerate foundation model development.
Remote · Canada
Review AI-generated research tables for accuracy, relevance, and completeness, verifying entries against linked primary sources. Conduct independent web research to find missing information and complete a qualification assessment before beginning live review tasks.
Remote · Canada
Create realistic HVAC diagnostic and system-design scenarios, then write reference answers explaining the technical and code reasoning behind each step. Evaluate AI-generated responses for accuracy, efficiency, and safety, and identify plausible-sounding but dangerous or technically incorrect advice.
Remote · Canada
Author realistic health information management scenarios and reference answers covering privacy, release of information, and record integrity. Evaluate AI model responses for regulatory accuracy and disclosure risk, and flag guidance that could breach privacy or compromise records.
Remote · Canada
Create realistic fraud investigation scenarios and reference answers that explain the reasoning behind investigative decisions. Evaluate AI model responses for soundness, evidentiary rigor, and completeness, and flag unsupported conclusions.
On-site
Create original, research-grade AI evaluation tasks based on computational work you have personally performed, and define metrics for judging strong solutions. Revise tasks in response to structured review feedback and optionally review or calibrate tasks submitted by other experts.
On-site
Design original, research-grade AI evaluation tasks based on computational work the author has personally performed, including defining connected subproblems, reference solutions, and scientific-result tests. Specify evaluation metrics, revise tasks in response to review feedback, and optionally review or calibrate tasks from other experts.
Remote · Canada
Author realistic statistics scenarios and reference answers covering study design, analysis, and interpretation. Evaluate model outputs for methodological soundness and correct interpretation, and flag analyses that draw invalid conclusions.
Remote · Canada
Create realistic care coordination scenarios from admission through post-acute placement and write reference answers explaining level-of-care decisions. Evaluate AI model responses for clinical appropriateness and benefit accuracy, and flag plans that could leave patients without appropriate care or lead to denials.
Remote · Canada
Create realistic primary classroom scenarios and reference answers that explain the developmental reasoning behind instructional choices. Evaluate AI model outputs for age appropriateness and instructional accuracy, and identify activities that are engaging but lack educational value.
Remote · Canada
Create tax accounting questions and case studies covering tax preparation, planning, compliance, and related topics to challenge AI models. Evaluate model responses for accuracy and alignment with tax accounting best practices and IRS regulations, and collaborate with tax and technical experts to refine the content.
Remote · Canada
Develop civil engineering questions and case studies across infrastructure and structural disciplines to challenge AI models. Evaluate model responses for technical accuracy and compliance with engineering standards, and collaborate with experts to refine content difficulty and educational value.
Remote · Canada
Design realistic technical scenarios and problem sets, then author expert-level reference solutions and grading rubrics. Evaluate submitted work for correctness, depth, and sound domain judgment.
Remote · Canada
Review, label, and evaluate gaming-related data, including text, game content, and AI model outputs. Use gaming expertise to assess content accuracy, quality, and relevance, and create prompts to further evaluate games.
Remote · Canada
Create grading rubrics, exemplar student responses, research briefs, and instructional materials that reflect high-quality high school coursework. Evaluate AI model outputs and identify issues with reasoning, structure, clarity, and pedagogy.
On-site
Design original, research-grade AI evaluation tasks based on computational work from your own earth, ocean, or climate science research, including a Python reference solution and tests. Define evaluation metrics, revise tasks in response to review feedback, and optionally review or calibrate tasks submitted by other experts.
Remote · Canada
Review, label, and evaluate text, documents, model outputs, and domain-specific content using project guidelines and professional expertise. Provide structured, reasoned annotations with citations, document decisions consistently, and flag ambiguous or out-of-scope samples.
Remote · Canada
Develop property management questions and case studies covering operational topics such as leasing, tenant relations, maintenance, budgets, and legal compliance. Evaluate AI model responses, provide detailed feedback, and collaborate with real estate and technical experts to refine the difficulty and educational value of the content.
On-site
Record yourself reading a provided short script and follow the step-by-step recording guide. Submit the recording through the designated platform.
Remote · Canada
Create realistic biology scenarios and reference answers that explain the scientific reasoning, mechanisms, and evidence behind conclusions. Evaluate AI model responses for biological accuracy, evidence handling, and appropriate uncertainty, and identify fluent but scientifically incorrect explanations.
Remote · Canada
Create linguistic evaluation scenarios and write reference analyses that explain judgments, supporting data, generalizations, and exceptions. Evaluate model responses for analytical accuracy and sound handling of linguistic data, flagging misparses and incorrect labels.
