Accepting Applications
Full-time
Remote
LinkedIn
Posted 3 weeks, 1 day ago
5 views
0 applications
Job Description
Work Snapshot
Type: Contract
Commitment: 15–20 hours per week minimum
Pay: $90–$110/hour (weekly payments via Stripe or Wise)
What You'll Be Doing
- Author complex, multi-step benchmark tasks grounded in real-world workspace files including technical specs, architecture docs, API references, and codebases
- Design tasks that evaluate the ability of language models and systems to reason over technical documentation and follow precise instructions
- Pair each task with a clearly defined ground truth output and an objective evaluation rubric
- Incorporate web search and code execution into task design to reflect professional, real-world workflows
- Contribute to the development of benchmark datasets used to assess LLMs on professional document understanding and instruction following within the Technology domain
What We're Looking For
- Strong experience in software engineering, data science, or analytics in a hands-on professional capacity
- Strong experience in authoring or evaluating technical documentation, including architecture docs, API references, or codebases
- Strong experience in designing structured, multi-step tasks with measurable outputs and evaluation criteria
- Strong experience working independently in a remote, self-directed contract environment
How To Apply
- Submit application via Mercor's platform
- Complete screening or assessment as directed
- Engage as an independent contractor upon selection