about 1 month ago
Prague, CzechiaSenior / Staff+
Responsibilities
- Build a distributed system for millions of AI agents.
- Develop an orchestrator for sandbox placement on nodes.
- Implement support for sandbox live migrations.
- Ensure smooth self-hosting developer experience for open-source.
- Optimize sandbox startup times to under 200ms.
- Scale the system to support billions of sandboxes simultaneously.
- Create an observability stack starting at the kernel level.
Requirements
- 7+ years of experience in building distributed systems at scale.
- Deep expertise in Linux internals and kernel-level debugging.
- Experience with VM hypervisors like Firecracker or QEMU.
- Strong programming skills in Go, Rust, or C/C++.
- Production orchestration experience with systems like Kubernetes or Nomad.
- Performance optimization skills with a focus on latency reduction.
- Strong networking knowledge, including L4/L7 load balancing.
Benefits
- Full healthcare, vision, and dental insurance coverage.
- Unlimited PTO policy.
- In-person collaboration in Prague or San Francisco.