Founding AI Engineer

The Core Responsibilities For The Job Include The Following

AI Infrastructure and Architecture:

• Lead AI infrastructure in production environments.
• Design and implement multi-agent systems with deep retrieval capabilities.
• Build robust context management systems that maintain design intent across sessions.
• Optimize agent coordination, communication patterns, and decision-making workflows.
  

Product And Research Integration

• Translate cutting-edge AI research into working features that designers actually use.
• Implement advanced retrieval-augmented generation (RAG) systems for design knowledge.
• Build context-aware agents that understand design patterns, user preferences, and project history.
• Work closely with founders and the early team to shape product direction.
  

Technical Leadership

• Drive core technical and product decisions around AI capabilities.
• Establish best practices for agent evaluation, monitoring, and continuous improvement.
• Scale AI systems to handle complex, multi-step design workflows.
• Own the full stack from model fine-tuning to production deployment.
  

Requirements

• Production AI Experience: Built AI agents in production with real users (web-socket, async, gRPC).
• Multi-Agent Systems: Experience implementing and evaluating complex agent architectures.
• Retrieval and Context: Deep experience with RAG systems, vector databases, and context management.
• Strong Engineering: Solid software engineering fundamentals with a focus on scalable, maintainable systems.
• Communication: Clear communication with engineers, designers, and non-technical stakeholders.
  

Nice To Have

• Experience with design tools, creative workflows, or visual AI.
• Like to do product thinking and how to shape the product.
• Previous startup experience in fast-paced, high-ownership environments.
  

Tech Stack You'll Work With

• AI/ML: OpenAI, Anthropic, or similar LLM APIs.
• Retrieval: Vector databases (Pinecone, Weaviate, Chroma).
• Backend: Python, HTTP/2 connections, async processing.
• Infrastructure: Cloud platforms (AWS/GCP), Docker, and monitoring tools.
• Tools: Cursor for development, internal tooling as needed.