Senior Software Engineer, Observability Insights
Core
Building the next-generation insights layer for AI systems by transforming telemetry into actionable insights for internal and external users.
Role type
Senior Software Engineer (Observability & Agentic Interfaces)
Builds
Multi-tenant APIs, managed Grafana experiences, and MCP-based tool servers
Domain
AI Infrastructure / Observability
Deliverable
production ML models | product features
Required skills
Backend systems engineering, distributed APIs, reliability engineering (SLOs, error budgets), observability systems (ClickHouse, Loki, VictoriaMetrics, Prometheus, Grafana), agentic applications, LLM grounding, tool calling, Go, Python
Preferred skills
Kubernetes cluster operations at scale, logging/tracing/metrics platform deep knowledge, distributed systems/event streaming, LLM frameworks (Langchain, AgentCore)
Responsibilities
Design multi-tenant APIs and managed Grafana experiences, develop MCP-based tool servers, build agentic interfaces for telemetry interaction, collaborate on end-to-end observability experience
Seniority
Senior, hands-on IC
