Backend Engineer: AI-Driven Incident Investigation & Orchestration

Kloudfuse; Cupertino, Northern (CA, KY); Hybride; USD 150 000 - 230 000; Plein temps

Résumé du poste

Kloudfuse is building an agent fleet that investigates live production incidents, orchestrating multi-agent loops and handoffs, with real telemetry and KPIs to evaluate outcomes.

You will wire agents to observability data via MCP tools, shape guardrails, and ensure safe autonomous operation in production environments. We ship first, then iterate, with hands-on ownership from week one.

Qualifications

• Backend engineering experience in distributed systems.
• Experience building agentic systems with multi-step planning.
• Ability to assess autonomy and safety in unattended operations.
• Experience reasoning about production incidents.

Responsabilités

• Build the agent fleet that investigates live production incidents.
• Design multi-agent orchestration and handoffs between agents.
• Wire agents to observability data through MCP tools and telemetry sources.
• Build evaluation harnesses to measure correctness of investigations.
• Ship guardrails with least-privilege tool surfaces and permission models.

Connaissances

Backend engineering

Distributed systems

Agentic systems

SRE awareness

Outils

MCP tools

Observability data

Description du poste

Kloudfuse is building an agent fleet that investigates live production incidents, orchestrating multi-agent loops and handoffs, with real telemetry and KPIs to evaluate outcomes.

You will wire agents to observability data via MCP tools, shape guardrails, and ensure safe autonomous operation in production environments. We ship first, then iterate, with hands-on ownership from week one.