Founding AI / Reliability Engineer

Role overview Build production systems that detect, diagnose, and resolve failures in blockchain infrastructure. This founding engineering role spans AI, distributed systems, observability, and site reliability, with a focus on making operational decisions safely and verifying that automated fixes work.

Responsibilities - Correlate metrics, logs, traces, node health, and RPC behavior to investigate incidents. - Diagnose unhealthy nodes or upstream providers and choose suitable recovery actions. - Automate actions such as restarting or reconfiguring infrastructure and rerouting traffic. - Verify recovery, improve root cause analysis, and turn recurring incidents into automated workflows. - Develop agent context, tool execution, orchestration, and evaluations for production operations. - Add safeguards such as permissions, rollback, confidence checks, observability, and blast radius controls.

Requirements - Experience building AI agents or LLM systems that use tools to take actions. - Ability to evaluate models and agent designs for reliable production use. - Skills in observability, SRE, or distributed systems operations. - Sound judgment about validation, permissions, rollback, testing, and safe execution. - Familiarity with blockchain infrastructure, client behavior, or configuration is relevant to the work.

Benefits and work setup - Full-time and remote-first. - Early ownership of a core technical area, with direct founder access and influence over product and architecture. - Meaningful stock options through an employee stock ownership plan.