Job Description
About The Role
n
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.
n
What you'll do
n
n
Design and implement world state management for multi-agent systems
n
Build high-throughput inference serving infrastructure
n
Implement distributed coordination for tool execution
n
Optimize memory hierarchy for large-scale deployments
n
Ensure reliability and observability across the stack
n
n
Requirements
n
n
5+ years experience in distributed systems or infrastructure
n
Solid experience with Python and at least one systems language (Rust, Go, C++)
n
Deep understanding of databases, caching, and storage systems
n
Experience with Kubernetes and cloud infrastructure (AWS/GCP)
n
Track record of building reliable, high-performance systems
n
n
Nice to have
n
n
Experience with ML serving infrastructure (Triton, vLLM, etc.)
n
Background in real-time systems
n
Familiarity with vector databases and embedding systems
n
#J-*****-Ljbffr

📌 Systems Engineer - Distributed Systems (Victoria)
🏢 Engram
📍 Victoria