SRE, Fleet Command & Control for Frontier Inference

Etched.ai; San Jose (CA); On-site; USD 200,000 - 260,000; Full time

Benefits offered by this job

Medical, dental, and vision packages

Relocation support

Housing subsidy

Daily lunch and dinner

Unlimited compute budget

Wellness benefits

Job summary

Etched, a hardware-first frontier AI company in San Jose, is seeking a Site Reliability Engineer to design and run scalable systems for inference workloads. You will define healthy signals, build alerting standards, and automate recovery across fleet management and telemetry layers.

You’ll collaborate with software, hardware and field teams to reduce downtime and improve operator experience. You will join a hands-on team in a fast-moving, in-person environment, owning on-call rotations, incident

Qualifications

• 2+ years in site reliability or production engineering for large-scale systems.
• Experience defining alerting standards with SLOs and incident management.
• On-call experience for externally used services.
• Debugging production incidents using logs, metrics, traces.
• Programming or scripting in Python, Go or Rust.
• Experience with Linux, containers, Kubernetes, and IaC (Terraform/Ansible).
• Familiar with hardware in the loop and PCIe issues.
• Strong written communication and cross-team alignment.

Responsibilities

• Define healthy inference system signals and actions.
• Set cross-team alerting standards with SLOs.
• Reduce alert noise during deploys and maintenance.
• Automate recovery with runbooks and guardrails.
• Route events to the right engineer with context.
• Shape fleet data and reporting with OpenTelemetry.
• Own incident management lifecycle and on-call rotations.
• Advise on canaries, rolling deploys and graceful drain.
• Share on-call in follow-the-sun rotation.

Skills

SRE experience

Incident management

On-call rotation

Logging metrics

Distributed tracing

Automation scripting

Education

Bachelor's degree in CS/Engineering

Tools

Prometheus

Grafana

OpenTelemetry

Kubernetes

Terraform

Ansible

Linux

Job description

Etched, a hardware-first frontier AI company in San Jose, is seeking a Site Reliability Engineer to design and run scalable systems for inference workloads. You will define healthy signals, build alerting standards, and automate recovery across fleet management and telemetry layers.

You’ll collaborate with software, hardware and field teams to reduce downtime and improve operator experience. You will join a hands-on team in a fast-moving, in-person environment, owning on-call rotations, incident