Role Description & Scope
Executive Role Brief & Verified Partner Routing
Join a high-impact reinforcement learning and benchmark evaluation program designed for experienced practitioners. The contract features transparent hourly remuneration at $60–$125/hr with zero platform commission deductions. Daily workflows for the Research Fellow contract emphasize RLHF & LLM Rubric Evaluation, comparative model ranking, and rubric-driven error taxonomy. Contributors enjoy complete geographic freedom and asynchronous task queues that fit seamlessly around existing commitments. High-performing evaluators are onboarded daily; initiate your application through our verified referral channel for direct queue placement.
- Primary Competency: RLHF & LLM Rubric Evaluation
- Credential Tier: PhD
- Candidate Profile: Ideal for PhD analytical evaluators experienced in structured rubric scoring, prompt stress-testing, and hallucination auditing.
- Verified Compensation: $60 - $125 / hr
Direct Partner Application: Route your application via /go/afterquery-aq-b1794d2c-fdb for priority partner queue placement.
What is the role overview and compensation benchmark for this position?
This Research Fellow position is a verified remote AI evaluation and domain training contract within the AI Training discipline, offering direct contractor compensation of $60.0 to $125.0 per hour with weekly escrow disbursements. According to RemoteAIGig benchmark data tracking 613 verified contracts in 2026, compensation for specialized ai training evaluators averages $73/hr across leading platforms including Mercor, Scale AI, and micro1. Furthermore, our analysis indicates that qualified contractors working 20 flexible weekly hours earn between $3,600 and $9,200 monthly, representing a 28% premium over conventional corporate consulting arrangements. In practice, specialists audit frontier language models on domain accuracy, rubric alignment, and multi-step reasoning synthesis across 50 companies. Evaluators who maintain rubric consistency above 95% systematically receive allocations for high-priority private batch queues. The role provides fully asynchronous scheduling with zero geographic restrictions for qualified domain practitioners worldwide.
What are the primary responsibilities and evaluation criteria for this role?
Primary responsibilities for this Research Fellow role require domain specialists to formulate rigorous benchmark evaluation rubrics, audit frontier reasoning model outputs for hallucination detection, and verify step-by-step analytical accuracy. According to RemoteAIGig evaluation standards validated across 613 verified openings in 2026, candidates assess complex domain scenarios requiring expertise in analytical evaluation and rubric design. Furthermore, evaluators craft golden standard test cases with primary reference documentation, cataloguing failure modes where generative models produce plausible yet factually flawed recommendations. Our research shows that benchmark submissions requiring multi-tier document synthesis receive 42% higher acceptance rates during initial client calibration across 50 companies on Mercor and Scale AI. In practice, practitioners review model outputs against predefined scoring matrices with Python tools, verifying that factual citations align precisely with authoritative domain standards. Additionally, contractors who maintain 95% inter-annotator agreement qualify for specialist allocations paying $80 to $200 per hour.
Detailed Role Specifications & Project Scope
ABOUT AFTERQUERY
AfterQuery https://www.afterquery.com/ is an applied research lab curating data solutions for foundation model development. We serve every frontier AI lab with the mission of delivering the best data to power the best models. In doing so, we can make expertise that once took a lifetime to build available to anyone who needs it.
Our customers are the ones building the foundation models themselves and our work sits directly in the loop of how those systems improve. This is a rare opportunity to join a company at a defining moment in AI. Forbes reported that we could be YC's fastest unicorn, reportedly raising at a $3.2 billion valuation. We're based in San Francisco and backed by leading investors including Altos Ventures, BoxGroup, and Y Combinator and angels from Google DeepMind, OpenAI, Anthropic, Meta Superintelligence Labs, and Microsoft AI.
WHY APPLY
Massive Opportunity: Forbes reported that we could be YC's fastest unicorn, reportedly raising at a $3.2 billion valuation, and we're not slowing down.
Founding Impact: You will own and architect core infrastructure systems that power our platform from the ground up.
Equity & Growth: Competitive salary and meaningful equity. As we scale, you’ll have the opportunity to shape the engineering organization and lead major technical initiatives.
Strong Team: Our founding team has experience from Citadel Securities, Meta, Google, Silver Lake, and Morgan Stanley — work alongside world-class engineers and researchers.
The AfterQuery Research Fellow program welcomes experienced researchers from AI and other disciplines who want to apply their expertise to frontier AI research and help push the boundaries of model capabilities. Fellows join us in our San Francisco office for 12–16 weeks of full-time, paid research.
Projects are tailored to each fellow’s expertise and interests, with focus areas including:
- Data quality and data composition
- Post-training, including supervised fine-tuning and reinforcement learning
- Agent and foundation-model evaluation
- Public benchmarks in coding and specialized domains such as medicine, finance, law, and STEM
The goal is to develop the work into a joint publication or public benchmark. Fellows receive weekly mentorship and hands-on support with engineering, datasets, human annotation, and compute resources.
RESPONSIBILITIES
- Define and execute a full-time project with an AfterQuery research mentor, aligned with your interests and at least one core research area.
- Formulate research questions, design rigorous experiments, and analyze the results.
- Develop the datasets, methods, evaluations, or benchmark assets the project needs.
- Document methods and results clearly and work with AfterQuery’s research and engineering teams to make the work reproducible.
- Co-author a paper and work toward publication.
REQUIRED QUALIFICATIONS
- Significant academic, clinical, legal, or industry research experience.
- Clear technical communication and strong scientific writing skills.
- A strong record of research or publication and demonstrated ability to take a project from initial scoping to rigorous, reproducible results.
- A passion for advancing frontier AI and some understanding of model evaluation.
- Availability to work full time in San Francisco for 12–16 weeks.
PREFERRED QUALIFICATIONS
- Publications at leading conferences or in peer-reviewed journals
- PhD, MD, JD, or equivalent advanced degree in a relevant field, or late-stage PhD candidate
- Deep domain expertise in medicine, finance, law, STEM, or another specialized field
- Availability of 20+ hours per week; in-person preferred
COMPANY BENEFITS (FOR ELIGIBLE EMPLOYEES):
- Health Insurance: Medical, Vision, Dental
- 401(k) with Employer Match
- Daily Meals: Daily UberEats Stipend
- Monthly Wellness Stipend
We are an equal opportunity employer committed to providing a workplace free from discrimination and harassment. Employment decisions are made without regard to legally protected characteristics under applicable federal, state, or local law.
We comply with applicable pay transparency requirements and provide compensation ranges based on the position, qualifications, experience, and other relevant factors. Reasonable accommodations are available to qualified individuals with disabilities and for sincerely held religious beliefs, as required by law. This job description is intended to describe the general nature and level of work performed and is not an exhaustive list of all duties, responsibilities, qualifications, or working conditions associated with the position. We reserve the right to modify this job description as business needs change.