Full Stack Engineer, AI systems

Overview

Build full-stack product features that turn AI capabilities into reliable, production-grade workflows. The role focuses on agent behavior, real-time interactions, integrations, and dependable task completion.

What you'll do

• Build end-to-end features across frontend, backend, and AI integrations.
• Design multi-step agent workflows for planning, tool use, failure, and recovery.
• Integrate LLMs, memory, and external tools into reliable systems.
• Design real-time AI interactions with streaming and partial results.
• Improve reliability, observability, latency, and fallback mechanisms.
• Collaborate with ML, backend, and product teams to ship features.
• Iterate based on real usage and workflow failure modes.

What you'll need

• Strong full-stack engineering experience across frontend and backend.
• Understanding of system design and API architecture.
• Experience with LLMs, RAG systems, or AI-powered applications.
• Ability to make pragmatic engineering decisions in ambiguous situations.
• Strong ownership of features from idea through production.
• Comfort working with evolving requirements in fast-moving environments.
• Experience with technologies including Next.js, Python, Node.js, PyTorch, SQL or NoSQL, Kubernetes, or Docker.

Details

• Location: United States.
• Interviews may be conducted virtually or onsite.