Applied AI Engineer: Shape Self-Improving Design Agents

Magic Patterns; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Rapid career growth

Equity package

20 days off PTO

Health, dental, and vision coverage

Team offsites and events

Job summary

Magic Patterns seeks an AI-focused engineer to own the eval system powering a self-improving agent loop and to push the boundaries of AI-driven design. You will collaborate with product teams to translate user perspectives into robust AI solutions, shaping how our design agent evolves.

You will work on eval systems, post-training, and context engineering, combining first-principles thinking with practical experimentation to drive product excellence.

Qualifications

• Experience building eval systems for AI agents.
• Experience with AI models and/or AI agents.
• 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.
• Collaborate with the product team to bring novel solutions to improve agent quality from the user's perspective.
• Decide what to work on to improve our AI Design agent.

Skills

Eval systems

Context engineering

AI agents

First-principles thinking

AI models

Job description

Magic Patterns seeks an AI-focused engineer to own the eval system powering a self-improving agent loop and to push the boundaries of AI-driven design. You will collaborate with product teams to translate user perspectives into robust AI solutions, shaping how our design agent evolves.

You will work on eval systems, post-training, and context engineering, combining first-principles thinking with practical experimentation to drive product excellence.