Remote AI Evaluation Specialist (Flexible Schedule)

Outlier (by Scale AI); City Of London; Remote; GBP 13,000 - 18,000; Full time

Benefits offered by this job

Flexible schedule

Remote work from anywhere

Free access to leading LLMs

Join 900K+ Outlier Experts across 52+?

Weekly payments

Job summary

Outlier, an AI training platform by Scale AI, is seeking detail-oriented English speakers to review AI-generated media. You'll roleplay live conversations with an AI voice model, score exchanges, and explain what looked or sounded off, remotely on your schedule.

You'll compare AI-generated images and videos, rate adherence and realism, and provide concise, evidence-based explanations. This freelance, 1099 role offers flexible hours, weekly payments, and access to leading LLMs.

Qualifications

• Fluent English with clear written communication.
• Strong attention to detail and ability to replay or zoom in on data.
• Able to think on your feet and discuss scenarios naturally.
• Experience writing short, evidence-based explanations.
• Able to make a clear decision when two options have flaws.
• Nice to have a Bachelor's degree or higher.

Responsibilities

• Holding a live, scenario-based conversation in English with AI voice models, then ranking naturalness and usefulness.
• Comparing pairs of AI-generated images and videos and judging which follows the prompt better.
• Inspecting outputs closely to spot problems like distorted anatomy, flickering, or mismatched audio.
• Rating each output on adherence, quality, and realism, with written explanations.

Skills

Fluent English

Attention to detail

Think on your feet

Experience writing explanations

Decision making

Bachelor's degree (nice to have)

Education

Bachelor's degree

Job description

Outlier, an AI training platform by Scale AI, is seeking detail-oriented English speakers to review AI-generated media. You'll roleplay live conversations with an AI voice model, score exchanges, and explain what looked or sounded off, remotely on your schedule.

You'll compare AI-generated images and videos, rate adherence and realism, and provide concise, evidence-based explanations. This freelance, 1099 role offers flexible hours, weekly payments, and access to leading LLMs.