Applied AI Engineer: Own Self-Improving Design Agent Loop

Magic Patterns; San Francisco (CA); Hybrid; USD 150,000 - 230,000; Full time

Benefits offered by this job

Rapid career growth

Competitive salary & equity

20 days PTO

Health, dental & vision coverage

Team offsites & events

Job summary

Magic Patterns in San Francisco is seeking an AI Engineer to own the eval system feeding our self-improving agent loop and to push the boundaries of what AI can achieve in design. You will collaborate with product to deliver novel solutions improving agent quality from user perspective, and decide what work to tackle next from open problems.

We highly value first-principles thinking, hands-on AI tooling, and a passion for building high-quality design outputs.

Qualifications

• Use AI tools in daily workflow
• Experience with AI models and/or have worked on an AI agent before
• Experience building eval systems, post-training, context engineering
• Strong first-principles thinker who can distill complex problems

Responsibilities

• Own our eval system that feeds into our self-improving agent loop
• Push and define the limits of what AI can do in design. Today, we are state of the art, and we want to continue to push that.
• Collaborate with the product team to bring novel solutions to improve agent quality from the perspective of our users
• Decide what to work on to improve our AI Design agent. The list above are open problems, not assignments

Job description

Magic Patterns in San Francisco is seeking an AI Engineer to own the eval system feeding our self-improving agent loop and to push the boundaries of what AI can achieve in design. You will collaborate with product to deliver novel solutions improving agent quality from user perspective, and decide what work to tackle next from open problems.

We highly value first-principles thinking, hands-on AI tooling, and a passion for building high-quality design outputs.