Senior Agentic Infra Engineer - Reliability & Ops

Socket.dev; Long Beach (CA); On-site; USD 154,000 - 230,000; Full time

Benefits offered by this job

Equity

Generous PTO

Learning stipend

Parental leave

Job summary

Relativity Space is seeking an experienced engineer to own and evolve our agentic infrastructure. You will deploy, operate, and secure complex systems across Linux/macOS, Proxmox, and GPUs, working closely with multi-disciplinary teams in a hands-on role.

You will improve observability, build internal tools, and contribute to open-source projects, while ensuring reliability and performance in production environments with strong networking and security focus.

Qualifications

• 5+ years building and operating complex software and compute infrastructure.
• Experience deploying an agentic harness (OpenClaw, Hermes, SybilClaw) in real environments.
• Strong Linux and macOS debugging, networking, and storage management.
• Experience operating physical infrastructure, VMs, or containers in production.
• Strong networking fundamentals: routing, VLANs, DNS, firewalls.
• Ability to build software and integrations when existing tools fall short.
• Experience contributing to/open-source projects.

Responsibilities

• Own the reliability of agentic infrastructure (agents, sessions, routing, pipelines).
• Build and maintain custom infrastructure where off-the-shelf tooling falls short.
• Deploy and operate local LLM inference on Mac Studio and GPUs.
• Manage Linux/macOS systems, Proxmox VMs/containers, storage and backups.
• Maintain multi-site networking: routing, VLANs, DNS, firewalls, connectivity.
• Build CLIs, dashboards, automation, and internal tools to speed engineers.
• Improve observability, debugging, and automated failure recovery.
• Contribute upstream to open-source projects we rely on.
• Design security around local compute, data handling, and access controls.
• Package and deploy stack portions into internal and customer environments.
• Collaborate with engineers to turn recurring problems into better infra.

Skills

Agentic infrastructure

Linux

macOS

Networking fundamentals

OpenClaw/Hermes/SybilClaw

Production deployment

Open-source contributions

Tools

Proxmox VMs

CLIs & dashboards

Job description

Relativity Space is seeking an experienced engineer to own and evolve our agentic infrastructure. You will deploy, operate, and secure complex systems across Linux/macOS, Proxmox, and GPUs, working closely with multi-disciplinary teams in a hands-on role.

You will improve observability, build internal tools, and contribute to open-source projects, while ensuring reliability and performance in production environments with strong networking and security focus.