AI Coding Evaluator
Company shown to members 🔒 · Remote · Poland, Argentina, Chile +1 only
Apply free: 3 jobs are on us✨ Tailor my resume for this job🎤 Practise the interview question, free
✓ Straight from the company's own careers page. No middlemen, no “we'll send you a check for equipment”. How we check jobs
✓ Sent 100 applications and heard nothing? Make this one count: tailor your resume to this ad in one tap, free.
✨ Not sure this is the one? Get your remote job matches in 30 seconds →
First recorded by Psst: 12 October 2026. Your first 3 jobs are free to apply to (the first right away, 2 more with your email). After that, the company and the apply link are for Psst members, from $4.99 for 7 days.
Practise the first interview question for this job
If the company replies, the first call usually starts with a question like this. Vague answers are the easiest to reject. Write yours and get an AI score in under a minute.
The 20-second read
- Experience
- Experience not stated
- Where you can live
- Poland, Argentina, Chile +1 only
- Languages
- Portuguese, French, German, Italian
- Skills and tools
- quality assurance, troubleshooting, technical support, written communication, customer service
- Job type
- Full-time
Read from the ad by Psst's rules. Check the full ad below before applying.
Job details
- Where you can work
- Poland, Argentina, Chile, Uruguay
- Employment type
- Full-time
- Advertised pay
- Not stated by the employer
- Experience
- Experience not stated
- Employer publication date
- 12 October 2026
- First recorded by Psst
- 12 October 2026
- Last checked at the source
- 10 November 2026
About the job
Help shape the future of AI by evaluating the technical accuracy, language quality, and usefulness of AI-generated responses.
- Location: Remote
- Type: Independent contractor / Part-time
- Project duration: up to 3 months
ABOUT THE ROLE
At the company, we create high-quality training and evaluation data for frontier AI models.
We’re looking for multilingual experts with coding knowledge and a solid understanding of JSON to evaluate AI-generated technical content and customer service responses.
In this role, you’ll assess whether outputs are clear, helpful, natural, technically accurate, and aligned with project guidelines. Your evaluations will help improve both the customer experience and the technical reliability of AI systems.
WHAT YOU’LL DO
- Review AI-generated customer service responses and technical content.
- Evaluate responses for clarity, helpfulness, natural language, and overall quality.
- Assess technical correctness using your coding knowledge.
- Read, validate, and troubleshoot JSON, identifying structural and formatting issues.
- Check outputs for formatting accuracy and adherence to project guidelines.
- Provide clear, well-reasoned feedback explaining your evaluations.
WHAT WE’RE LOOKING FOR
- Fluency in one or more of the supported language varieties listed below.
- A solid understanding of JSON, including syntax, structure, validation, and troubleshooting.
- Coding knowledge sufficient to assess technical content and identify errors.
- Strong judgment when evaluating customer service responses.
- Excellent attention to detail and strong written communication skills.
- Ability to follow detailed evaluation guidelines consistently.
SUPPORTED LANGUAGES/LOCALES
- Dutch — Netherlands
- Welsh — United Kingdom
- French — Canada
- German — Germany
- Italian — Italy
- Portuguese — Brazil
- Greek — Greece
NICE TO HAVE
- Previous experience in AI evaluation, quality assurance, or technical support.
- Experience working with APIs and structured data.
- A background in customer service, software development, or technical writing.
VOICE RESPONSE INSTRUCTIONS
When completing the voice response, speak naturally and spontaneously, as if responding in real time. Do not pre-plan, write, or script your answer—we are evaluating natural voice cadence.
Responses may be up to one minute long. A few sentences are sufficient if that feels natural.
Apply free: 3 jobs are on us✨ Tailor my resume for this jobPrepare with the Apply kit
- No pay listed
A resume that gets past the first 6 seconds
Recruiters skim. The Psst resume coach fixes what makes them skip you, line by line, and one tap tailors it to 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, 6 designs, 8 colours and a matching cover letter, free to build. Premium downloads the PDF and Word files.
Example with made-up details. The score is the builder's own check, not an ATS rating or a promise of an interview.