Staff Engineer, Distributed Systems & Fleet Reliability

General Diffusion, Inc.; San Francisco, Northern (CA, KY); Hybrid; USD 160,000 - 220,000; Full time

Job summary

General Diffusion, Inc. is seeking a Member of Technical Staff to run and improve a multi-architecture testbed for research and experimentation.

You will own the fleet state, provisioning, and observability across heterogeneous hardware to ensure reproducible results. You will build dashboards and runbooks, drive incident response, and partner with teams to diagnose workload behavior on diverse silicon while maintaining reliability and auditable processes.

Qualifications

• Experience operating production distributed systems on Linux, including deployment, diagnosis, and day-two operations.
• Hands-on experience with bare-metal infrastructure and heterogeneous hardware lifecycles.
• Strong observability mindset using metrics, logs, and traces to guide triage and analysis.

Responsibilities

• Own inventory, provisioning, retirement, and readiness checks across the testbed; keep fleet state auditable.
• Develop repeatable experiment lifecycles from reservation to return-to-service.
• Capture context around real-world traces and failures to distinguish workload vs environment.
• Build fleet-health signals, dashboards, and alerts connecting hosts, networks, accelerators, and experiments.
• Maintain incident runbooks and lead post-incident improvements demonstrated through exercises.
• Collaborate with data infrastructure on evidence contracts.

Skills

Distributed systems

Linux

Bare-metal infrastructure

Observability & monitoring

Incident response

Job description

General Diffusion, Inc. is seeking a Member of Technical Staff to run and improve a multi-architecture testbed for research and experimentation.

You will own the fleet state, provisioning, and observability across heterogeneous hardware to ensure reproducible results. You will build dashboards and runbooks, drive incident response, and partner with teams to diagnose workload behavior on diverse silicon while maintaining reliability and auditable processes.