Agentic Tasker (Frontier STEM)
Turing • Europe, India, United States
Education
Bachelor's
Type
Hourly
Listed
25d ago
Apply opens Turing in a new tab.
Apply Now → ⚡ Boost your chances - Optimize your resume with Rezi.aiAbout this role
From the Turing listing
About the Role
Exciting opportunity to work directly with researchers at a top 8 Frontier Lab. The core objective of this role is to enhance the reasoning and problem-solving capabilities of a target frontier model in STEM topics by designing, validating, and analyzing challenging benchmark tasks.
Key Responsibilities
- Task Design and Development: Design challenging, real-world data science problems that serve as the foundation for Colab Bench tasks.
- Content Generation: Integrate the problems into an Agentic development environment, preparing all necessary components using Python, which include: Detailed Instructions and an overview of the required task. A Golden solution that follows the instructions. The necessary Environment, including datasets, Python libraries, and metadata. A Test notebook containing unit tests that solutions must pass.
- Evaluation and Analysis: Evaluate the cross model’s performance on the tasks
- Headroom Identification: Identify tasks where target model fails to pass all tests, specifically classifying the failure as a logical reasoning failure
- Loss Extraction: Analyze the agent’s steps (Agent Trajectory) to observe and extract core capability loss patterns from the model.
Qualifications and Recruitment
- Expertise Focus: Applicants must have strong expertise in data science, ML, finance, and coding, with a deep background in frontier STEM.
- Target Candidates: We are actively recruiting PhD students from top schools in the US and highly-skilled GitHub contributors. (Will consider a small cohort in India as well)
Offer Details
- Rate: ~ $80/hour.
- Commitment: Minimum 30 hours per week (on Week days).
- Employment Type: Contractor (no medical/paid leave).
- Duration: 3 months (expected start date: next week).
- Locations: North America, Europe.
How long hiring takes
Across the AI training platforms we refer candidates to, the median gap between referral and hire is about 30 days. It varies by platform and role, so treat it as a rough guide for this one.
Interview Prep
This listing calls for this tool directly. Prep for the technical screen:
What to Expect
Looking at Turing STEM listings we've tracked, contracts in this domain typically run about 8.5 weeks. Actual length varies by project, but this gives you a realistic baseline going in.
Based on 11 extracted Turing STEM listings.
Why this role
This Agentic Tasker role is for people with frontier STEM background to build and complete agentic tasks that test how AI agents handle multi-step scientific or technical workflows. The work requires enough STEM depth to design a task an agent can't shortcut its way through.
Talent pool
We're light on STEM candidates
We've matched 65 people with a STEM background against 726 STEM listings we've tracked, so most go out without one. Set up a profile and we'll consider you for a role like this one.
Set up your profileSkills and categories
Explore other opportunities in related specializations:
Related jobs
Browse All Jobs from Turing
Discover more opportunities on Turing that match your skills and interests.
View All Turing Jobs →Verified Reviews
Community Reviews
Share your experience with Turing
Help other candidates make better decisions by leaving a review.
Sign in to leave a reviewLeave your review
Common questions
How does Turing's talent matching work?
Turing calls it the Intelligent Talent Cloud. You build a profile and go through vetting (automated tests, an AI-powered interview, practical skill assessments), and once vetted, Turing's algorithm surfaces your profile directly to partner companies like Fortune 500s and top AI labs. You don't browse listings or bid on work; matches come to you.
How and when does Turing pay contractors?
Monthly, in USD, via Deel, Payoneer, or direct bank transfer. You're engaged as an independent contractor responsible for your own local taxes. Plan your cash flow around a monthly cycle if you're used to weekly payouts elsewhere.
What does task-based AI training work look like?
Practical, hands-on data work: recording short videos, categorizing images, rating text responses, or analyzing data. Tasks are designed to be short and distinct, typically 5 to 60 minutes each.
What does STEM work look like for an Agentic Tasker (Frontier STEM)?
Tasks here are scoped to STEM, not generic labeling. As an Agentic Tasker (Frontier STEM), expect to draw on real domain judgment (evaluating outputs, correcting errors, or providing expert reasoning specific to STEM) rather than following a one-size-fits-all rubric. If you don't have hands-on STEM background, this is likely not the right listing to start with.
What specific skills does this listing call for?
Coding and Python are named directly in the listing. If you don't have hands-on experience with these, expect the screening process to test for them directly rather than accepting adjacent experience as a substitute.
How much does this specific role pay?
The listing doesn't state a rate. The $15–$30/hr shown here is our estimate from the role type and location (see /pay-methodology), so treat it as a rough guide and confirm the actual rate with the platform before committing time.
What happens when I click Apply on this listing?
You'll be taken to Turing's external site to complete your application there. This listing links through a referral, but the process is identical to applying directly; the link just routes you correctly. Create an account on their site and follow their onboarding steps.
Can I apply from outside Europe, India, or the United States?
This specific role is open only to people based in Europe, India, and the United States. If you are somewhere else, applying is unlikely to lead to an offer even if you pass the assessment, because the restriction is usually about where the work can legally be contracted rather than your skills. Read the full description for any tax-residency or right-to-work caveats before you apply, since they can differ by country.