Systems Engineer - Distributed Systems

Our systems need to maintain world state, coordinate tool execution, and serve low-latency inference across distributed deployments. You'll build the infrastructure that makes our memory and reasoning systems reliable and performant at scale.

What you'll do

• Design and implement world state management for multi-agent systems
• Build high-throughput inference serving infrastructure
• Implement distributed coordination for tool execution
• Optimize memory hierarchy for large-scale deployments
• Ensure reliability and observability across the stack

• 5+ years experience in distributed systems or infrastructure
• Strong experience with Python and at least one systems language (Rust, Go, C++)
• Deep understanding of databases, caching, and storage systems
• Experience with Kubernetes and cloud infrastructure (AWS/GCP)
• Track record of building reliable, high-performance systems

• Experience with ML serving infrastructure (Triton, vLLM, etc.)
• Background in real-time systems
• Familiarity with vector databases and embedding systems