Staff Backend Engineer - Second Horizon
Core
Design and build the first production services for an AI-native context layer management system that enables AI agents to retrieve governed enterprise data and metadata.
Role type
Staff Backend Engineer (AI/LLM infrastructure)
Builds
Production-grade context ingestion, indexing, retrieval APIs, and agent-facing integrations for an observability platform.
Domain
Observability, AI/LLM infrastructure, Cloud-native systems
Deliverable
production ML models | product features
Required skills
LLMs, prompt engineering, GenAI application development, cloud-native architecture, observability tooling, API design, multi-tenant system design
Preferred skills
Agent frameworks, multi-agent workflows, data platforms (Snowflake, DataBricks), data engineering tools
Technologies
AWS, GCP, Azure, observability tools (metrics, logs, traces)
Responsibilities
Design and implement core backend services for context ingestion, indexing, and retrieval orchestration; Build scalable multi-tenant SaaS foundations with tenant isolation and quotas; Develop APIs for AI agents and MCP tools to retrieve context and provenance signals; Operate services using metrics, logs, and traces; Shape technical direction and engineering practices for the new product area.
Seniority
Staff, high-autonomy IC with architectural ownership
