AI Personal Assistant Quality Evaluator

Obsidian; San Francisco (CA); On-site; USD 34,000 - 83,000; Part time

Job summary

Obsidian in San Francisco is seeking advanced LLM power users to evaluate how AI systems perform on personalized, real-world life tasks. You will assess usefulness, realism, and practical success of AI responses in daily activities.

Ideal candidates regularly use AI tools in their personal lives and can explain what makes outputs good or bad, including multi-step planning, research, and decision-making. 20–40 hours per week engagement is expected.

Qualifications

• Experience using AI tools for everyday tasks and decision making.
• Ability to evaluate AI outputs for usefulness, realism, and personalization.
• Clear written explanations of what makes an AI output good or bad.

Responsibilities

• Evaluate AI responses across real-world life tasks and contexts.
• Judge usefulness, personalization, and success against user goals.
• Document criteria for good, bad, incomplete or unsafe outputs.

Skills

Heavy AI usage

Multistep task handling

Strong written judgment

Tools

ChatGPT

Claude

Gemini

Perplexity

Cursor

Windsurf

Codex

Job description

Obsidian in San Francisco is seeking advanced LLM power users to evaluate how AI systems perform on personalized, real-world life tasks. You will assess usefulness, realism, and practical success of AI responses in daily activities.

Ideal candidates regularly use AI tools in their personal lives and can explain what makes outputs good or bad, including multi-step planning, research, and decision-making. 20–40 hours per week engagement is expected.