Full-Stack Engineer

Introspection; San Francisco (CA); On-site; USD 140,000 - 190,000; Full time

Job summary

Introspection is seeking a Full-Stack Engineer to build the infrastructure behind production agent products. You will work across backend (Convex, Python), frontend (React), and deployment to make recipes, customer runtimes, and learning loops feel like one coherent platform.

You are a generalist who can own features from conception to production, enjoy shipping code quickly, and care deeply about product quality and user experience in the AI space.

Qualifications

• Proven experience building full‑stack web applications.
• Ability to move fluidly between frontend and backend.
• Interest in AI space and building tools for engineers.
• Focus on product quality and user experience.

Responsibilities

• Own features from conception to production.
• Collaborate across backend, frontend, and deployment infrastructure.
• Ship fast, iterate, and improve platform quality.
• Contribute to a cohesive platform for recipes, runtimes, and learning loops.

Skills

Full-stack development

Frontend & Backend bridging

AI-oriented

User experience focus

Tools

Convex

Python

React

Job description

We're looking for a Full-Stack Engineer to build the infrastructure behind production agent products. You'll work across our backend (Convex, Python), frontend (React), and deployment infrastructure to make recipes, customer runtimes, and learning loops feel like one coherent platform.

You might be a fit if...

You have proven experience building full-stack web applications and can move fluidly between frontend and backend.

You're interested in the AI space and want to build tools that help other engineers work more effectively with AI systems.

You care deeply about product quality and user experience, and you're not afraid to ship fast and iterate.

You're a generalist who enjoys working across multiple parts of the stack and can own features from conception to production.

About Introspection

Introspection is an applied AI team building the infrastructure for long-horizon vertical agents. We turn production conversations into evidence for better behavior, stronger quality gates, and more reliable releases.

We're a small, high-signal team based in San Francisco that values deep thinking, creative problem-solving, and shipping code that matters.