Indonesian AI Evaluator (Remote, Flexible Tasks)

Visa Hunt; Indonesia; On-site; IDR 202,986,000 - 289,102,000; Part time

Job summary

Productive Playhouse is seeking an Indonesian-speaking AI Evaluator to participate in structured evaluations of AI chatbots and language models. You will interact directly with models to assess capabilities, safety, and usefulness, delivering insights and data that inform model development.

Responsibilities include testing conversations, possibly voice interactions, and submitting deliverables such as write-ups and ratings.

Qualifications

• Native or expert-level fluency in Indonesian, as spoken in Indonesia.
• Strong English reading, writing, and communication skills - assessment maybe required
• 18 years of age or older
• Hands-on experience using AI models or large language models
• Comfortable with both written and voice-based conversation — and good at asking sharp follow-ups
• Your own smartphone, computer, reliable internet, and comfort with web-based tools
• Able to pass a language proficiency assessment and AI evaluation task
• Responsive communicator — quick replies move you through onboarding faster
• Able to start within 48 hours

Responsibilities

• Testing and evaluating AI chatbots or language models through structured conversations, using assigned goals and prompts.
• Voice-based interactions with AI models — for projects that involve this, sessions are recorded, and audio may be shared with the client as part of the evaluation deliverable.
• Submitting deliverables (write-ups, ratings, screenshots, or recordings) in the format each task specifies.

Skills

Indonesian fluency

English proficiency

Independent contractor

Communication skills

AI model experience

Tools

Smartphone

Job description

Productive Playhouse is seeking an Indonesian-speaking AI Evaluator to participate in structured evaluations of AI chatbots and language models. You will interact directly with models to assess capabilities, safety, and usefulness, delivering insights and data that inform model development.

Responsibilities include testing conversations, possibly voice interactions, and submitting deliverables such as write-ups and ratings.