Bilingual Evaluator - Fully Remote | Upto $50/hr

mercor; United States; Remote; USD 57,000 - 81,000; Full time

Job summary

Mercor — a San Francisco-based company — is seeking a Dutch Audio Generalist Evaluator for a 3–6 month contract. The role is remote, with compensation at $50/hour and requires working GMT or PST hours. You will transcribe Dutch and English audio, define evaluation rubrics, test model outputs, and support benchmarking with rigorous QA.

Ideal candidates are college students or graduates who can work independently, meet deadlines, and communicate fluently in Dutch and English.

Qualifications

• Fluent in Dutch and English.
• Strong writing and critical thinking skills.
• Ability to work independently and meet deadlines.
• Able to work within GMT or PST working hours.

Responsibilities

• Transcribe audio and video with precision in Dutch and English. Ensure adherence to multiple constraints and instructions.
• Define and document evaluation standards for consumer audio contexts. Develop comprehensive rubrics and guidelines in Dutch and English.
• Conduct model testing by running prompts and assessing outputs against expectations.
• Support benchmarking and quality assurance. Collaborate in QA review processes to ensure high standards of rigor.
• Maintain consistency and reliability before integration into official benchmarks. Work independently and meet deadlines.

Skills

Dutch language

English language

Strong writing

Independent work

Time zone familiarity

Education

College students or graduates

Job description

About the job Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark , General Catalyst , Peter Thiel , Adam D'Angelo , Larry Summers , and Jack Dorsey .

Role

Position: Dutch Audio Generalist Evaluator

Type: Contract

Compensation: $50/hour

Location: Remote

Duration: 3–6 months

Role Responsibilities

• Transcribe audio and video with precision in Dutch and English . Ensure adherence to multiple constraints and instructions.
• Define and document evaluation standards for consumer audio contexts. Develop comprehensive rubrics and guidelines in Dutch and English .
• Conduct model testing by running prompts and assessing outputs against expectations.
• Support benchmarking and quality assurance. Collaborate in QA review processes to ensure high standards of rigor.
• Maintain consistency and reliability before integration into official benchmarks. Work independently and meet deadlines.

Qualifications

Must-Have

• Strong writing and critical thinking skills
• Ability to work independently and meet deadlines
• Fluent in Dutch and English
• Able to work within GMT or PST working hours

Preferred

• College students or graduates

Originally posted on Himalayas