Technical Experts needed to stump AI Models
Lifted, an Upwork Company™ · Remote · US only
Apply on Lifted, an Upwork Company™'s sitePrepare with the Apply kit
First recorded by Psst: 2 November 2026. Sign in with Google to continue to the employer. A free account is enough.
The 20-second read
- Experience
- 10+ years required
- Where you can live
- US only
- Skills and tools
- linux, machine learning, onboarding
- Degree or licence
- Mentioned (masters)
- Job type
- Contract or freelance
Read from the ad by Psst's rules. Check the full ad below before applying.
Job details
- Where you can work
- United States
- Employment type
- Contract
- Advertised pay
- Not stated by the employer
- Experience
- 10+ years required
- Employer publication date
- 6 October 2026
- First recorded by Psst
- 2 November 2026
- Last checked at the source
- 3 November 2026
About the job
Experience level: not applicable.
Help build a benchmark of real, expert-level problems that today’s best AI agents still can’t solve. Experts take a genuinely hard problem from their own field and turn it into a task an AI must solve from scratch in a Linux terminal.
The goal: stump the model. A task counts only if, when three frontier AI models each try it three times, they mostly fail. It’s not annotation — contributors design the problems that expose where AI still breaks.
Who we need
- Masters degree or higher
- 10+ years of professional experience in a technical domain
- At least one publication (academic or professional)
Domains in demand
- Coding
- Machine Learning
- Systems
- Security
- Hardware
- This is an ongoing project — at least 7 weeks
- Onboarding process is approximately 90 minutes total
This enterprise client helps the world’s most innovative companies improve their AI models by providing human feedback.
Apply on Lifted, an Upwork Company™'s site
- No pay listed
Similar remote jobs
- Senior Technical Product Manager, AIUS only
- Senior Staff Technical Product Manager, Conversational AIUS only
- AI Technical Product Manager (QVAC) (100% remote)US, Ireland, Spain +1 only
- Head of Technical Program Management, Applied AIUS only
- Technical Program Leader - AI InfrastructureUS only
Explore more jobs
A resume that gets past the first 6 seconds
Recruiters skim. The Psst resume coach fixes what makes them skip you, line by line. Premium then shapes it for the exact job you're applying to.
- 1Every line checkedWeak starts, clichés and AI-sounding phrases flagged, with a 3-question fix.
- 2Tailored to the jobSee which skills and tools from the ad your resume is missing. Try it free on one of your matches.
- 3Ready for remoteTime zone, tools and proof you work on your own, the things remote teams look for.
- 4Looks the partOne page and an ATS-safe PDF, free. Premium adds 6 designs, 8 colours and a matching cover letter.
Example with made-up details. The score is the builder's own check, not an ATS rating or a promise of an interview.