Staff Software Engineer - AIOps
Core
Design, build, and operate the AIOps agent platform enabling AI agents to observe events, generate diagnoses, and execute approved actions within safety controls.
Role type
Staff Software Engineer (AIOps Platform)
Builds
Production AIOps agent runtime, tool interfaces, event routing, and operator experience for financial technology environments.
Domain
Financial Technology / AI Operations / Distributed Systems
Deliverable
production ML models | product features
Required skills
Python, distributed systems design, event-driven architectures, AI agent runtime development, tool-use/function-calling interfaces, production observability, front-end development (React/Next.js/Angular), TypeScript
Preferred skills
MCP integration patterns, Kubernetes automation, CI/CD platform integration, secrets management, auditability implementation
Technologies
Kafka, Pub/Sub, RabbitMQ, OpenTelemetry, Prometheus, Grafana, Kubernetes, React, Next.js, Angular, TypeScript, Python
Responsibilities
Design and operate the core agent runtime including event ingestion, planning, and response handling; Define and maintain scoped, auditable tool interfaces for agent interaction with infrastructure and ITSM platforms; Implement controls for agent actions including human approval workflows and emergency shutdown capabilities; Build event-routing capabilities to prioritize alerts and operational requests; Establish telemetry capabilities including logs, metrics, and traces; Develop evaluation capabilities for agent decision quality using historical replay and shadow-mode testing; Package reusable agent capabilities and APIs for self-service adoption by other teams; Develop and maintain the operator experience including approval workflows and decision history views.
Seniority
Staff, hands-on IC with strategic influence
