Architecture AI Benchmark Specialist — Remote (Part-Time)

Obsidian; San Francisco (CA); On-site; USD 55,000 - 110,000; Part time

Job summary

Mercor is seeking a contractor for a benchmark dataset project evaluating AI models on visual document understanding and instruction-following in the Architecture domain. The role is fully remote, approximately 15–20 hours per week, with a flexible schedule across US/Canada.

You will be engaged as an independent contractor, paid weekly via Stripe or Wise. Projects can be extended or concluded early depending on needs and performance, and we do not support H1-B or STEM OPT candidates at this time.

Qualifications

• Experience in AI model evaluation or benchmarking is a plus.
• Familiarity with visual document understanding tasks is beneficial.

Responsibilities

• Contribute to a benchmark dataset project evaluating AI models on visual document understanding and instruction-following in architecture domain.
• Collaborate asynchronously, deliver tasks on schedule, and document grounding outputs.

Job description

Mercor is seeking a contractor for a benchmark dataset project evaluating AI models on visual document understanding and instruction-following in the Architecture domain. The role is fully remote, approximately 15–20 hours per week, with a flexible schedule across US/Canada.

You will be engaged as an independent contractor, paid weekly via Stripe or Wise. Projects can be extended or concluded early depending on needs and performance, and we do not support H1-B or STEM OPT candidates at this time.