AI Personal Assistant 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

About the Opportunity

A leading AI research organization is seeking advanced LLM power users to evaluate how well AI systems handle personalized, real-world life tasks.

This role is for people who use AI tools heavily in their personal lives and can clearly judge whether an AI response is useful, personalized, realistic, and successful.

Who We're Looking For

Strong candidates have:

• Heavy personal usage of LLM products

• Experience using AI for multi-step tasks, planning, research, decision-making, or personal workflows

• Familiarity with tools such as ChatGPT, Claude, Gemini, Perplexity, Cursor, Windsurf, Codex, or other AI agents

• Ability to explain what makes an AI output good, bad, incomplete, unsafe, or unrealistic

• Strong written judgment and attention to detail

Why This Work Matters

LLMs are quickly becoming personal assistants for everyday decisions, but truly useful AI needs to do more than produce generic advice. It needs to understand context, preferences, constraints, tradeoffs, and what success looks like in real life. Your evaluations will help improve how AI systems support people with practical, high-context tasks across food, health, productivity, careers, and learning. This work directly contributes to making AI assistants more personalized, trustworthy, and useful for real-world personal workflows.

Engagement Details

• Expected commitment: 20-40 hours/week