Role Overview

The Role

• Build AI Memory (Beyond Vectors): Our current vector-based memory is hitting its limits. You'll lead the charge to design and implement our next-generation memory system This means solving hard problems in:
  • Scale Our Data & Retrieval Pipelines: As we grow, you'll be responsible for ensuring our data ingestion, hybrid search (BM25 + vector), and re-ranking pipelines are fast, reliable, and cost-effective.
  • Security: Ensure our infrastructure is highly secure and observable, with a focus on speed and cost
  • Graph-based Retrieval: How do you query a graph efficiently to provide the agent with rich, structured context, moving beyond simple semantic search?

• Architect a Scalable, Debuggable Agentic System: Our agent is a multi-step, tool-using system.
  • You'll design clean interfaces between the agent's "brain" (the planner) and its "hands" (the tools/modalities).
  • You'll build the debugging and observability tools necessary to understand why an agentic flow failed, which is one of the hardest challenges in this space.

Required Skills

• Deep experience building and scaling data-intensive backend systems in Python or Go.
• Strong system-design skills and experience working with distributed systems.
• A clear mental model for data structures and their trade-offs. You like to think deeply about how to represent complex information.
• Hands-on experience with RAG pipelines, even if you're a little frustrated with their limitations.
• Production experience with modern cloud infrastructure, observability tooling, and PostgreSQL
• A pragmatic approach. You know when to build for the long term and when to ship a clever solution that works now.

Benefits

• Remote-friendly work environment
• Collaborative team culture
• Opportunity to shape infrastructure decisions
• Competitive compensation packages including stock and health benefits, paid time off, and parental leave. 401k options for all US-based employees.
• Flexible working hours across multiple time zones