Graduate-Level Science Evaluator
Mercor is seeking PhD holders, doctoral candidates, and exceptional Master's graduates in biology, physics, chemistry, or related disciplines to join a high-impact AI research initiative in partnership with a leading AI lab.
This role involves evaluating and enhancing large language models (LLMs) by applying deep subject-matter expertise in graduate-level science to rigorously benchmark model performance.
Key Responsibilities
- Evaluate the accuracy, scientific depth, and domain relevance of LLM-generated answers in biology, physics, and chemistry.
- Review outputs across advanced topics such as molecular biology, genetics, classical mechanics, quantum physics, physical chemistry, and more.
- Complete structured evaluations for each task using an 8–10 question rubric and provide concise written feedback for each judgment.
- Identify factual inaccuracies, logical flaws, and reasoning gaps.
- Work independently and asynchronously using provided tools and guidelines.
You’re a strong fit if you have:
- A PhD (or are currently a PhD candidate) in Biology, Physics, Chemistry, or a related STEM field.
- Deep familiarity with graduate-level science curricula and research-level problem solving.
- Strong ability to critically assess scientific reasoning, technical writing, and analytical clarity.
- Excellent written communication skills and attention to detail.
- Comfort working independently and asynchronously in a remote environment.
- Basic understanding of Python or willingness to learn is preferred, but not required.
Role Details
- Part-time (10–20 hours/week) with flexible scheduling.
- 100% remote and asynchronous — work from anywhere, anytime.
Compensation & Legal
- Contractor position via Mercor, paid hourly.
- Competitive rates based on domain expertise, ranging from $35 to $60/hour.
- Weekly payments processed securely through Stripe Connect.
About Mercor
Mercor is a San Francisco-based company specializing in connecting elite professionals with cutting-edge AI initiatives. Our investors include Benchmark, General Catalyst, Adam D’Angelo, Larry Summers, and Jack Dorsey. We help leading AI labs accelerate progress by bringing in top-tier human expertise.
Average salary estimate
If an employer mentions a salary or salary range on their job, we display it as an "Employer Estimate". If a job has no salary data, Rise displays an estimate if available.
Mercor seeks experienced Radiologists in the US, UK, or Canada to contribute clinical expertise as independent contractors on a short-term AI research and question-design project.
Mercor seeks seasoned accounting and audit professionals (US/UK/Canada) to help train and validate AI systems by reviewing and improving AI-generated financial reporting, audit, and compliance outputs.
Kiddom is hiring a Spanish Translation Curriculum Writer to translate and adapt K-12 instructional materials into culturally relevant Spanish content for US-based learners.
Tenure-track Assistant Professor in archaeological materials and ancient technologies needed to teach in-person undergraduate courses, develop on-campus laboratory opportunities, and pursue an active research program at Wesleyan University.
Teaching Lab is hiring a mission-driven Future Coach/Facilitator to lead and facilitate teacher professional learning that advances educational equity across partner networks.
Mercor seeks experienced physics researchers to work remotely as contractors evaluating and calibrating AI-generated physics models and simulations across advanced domains.
Lead hands-on, in-practice training across the New York Metro area to drive rapid adoption of Dandy's intraoral scanning and digital dentistry workflows.
Provide evidence-based teletherapy to school-aged students across Florida as a licensed or associate clinician working remotely with a supportive, mission-driven team.
Teach infants and toddlers in a culturally responsive Muckleshoot Tribal program by developing and delivering age‑appropriate lessons, conducting screenings, and partnering with families.
Provide evidence-based remote teletherapy to North Carolina students as a licensed clinician (LCMHC/LICSW/LMFT) while collaborating with schools and families to support youth mental health.
Provide teletherapy to Kentucky students and families as a licensed mental health clinician on a flexible 1099 contract with competitive hourly rates and strong administrative support.
Provide evidence-based teletherapy to Florida students as an Associate Mental Health Therapist at Daybreak Health, collaborating with schools and families to support youth mental health.
Daybreak Health is hiring a bilingual Spanish-speaking Associate Mental Health Therapist (LCSW-A) to provide remote teletherapy to students while residing in Charlotte, NC for required in-person supervision.
Lead clinical operations and supervise a small caseload as the BCBA Clinical Director at a growing EIBI center in Fort Worth, shaping care delivery and staff development.
Teach and nurture preschool children at Lionheart Children's Academy in Tomball, delivering developmentally appropriate and Christ-centered early education.
We use AI to understand human ability and match talent with the opportunities they're best suited for.
76 jobs
🔮
Hi, I'm Risa! Your AI Career Copilot
you, just ask me below!
