Staff Backend Engineer, AI-Powered Context SaaS

Grafana; United States; Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity

Grafana Shutdown Days

Job summary

Grafana Labs, the company behind the open observability cloud, is hiring a Staff-level Backend Engineer to build the first production services for a context layer management system. The role focuses on ingest, storage, retrieval APIs, and agent integrations in a high-autonomy, production-grade environment.

The position is fully remote for candidates in the U.S. or Canada, with a strong emphasis on owning architecture, reliability, and cross-functional collaboration.

Qualifications

• Experience building production-grade software systems.
• Ability to tackle complex engineering problems with minimal supervision.
• Practical AI experience and familiarity with GenAI workflows.
• Comfort with ambiguity and defining scope where unclear.
• Strong communication across product, infra, and engineering teams.

Responsibilities

• Design and ship core backend services for context ingestion, indexing, and retrieval.
• Define a scalable multi-tenant SaaS foundation with tenant isolation and governance.
• Build APIs for AI agents, MCP tools, CLIs, and internal apps to access context and signals.
• Collaborate with product and infra to balance rapid experimentation with reliability.
• Instrument services with metrics, logs, traces, and dashboards for observability.
• Contribute to architecture, storage choices, and deployment patterns for a new product area.
• Communicate effectively across teams and own the AI solutions end-to-end.
• Ensure solutions are scalable, maintainable, and aligned with customer workflows.

Skills

Production-grade software

Self-starter

AI with practical mindset

Work under ambiguity

Cross-team communication

Tools

AWS

GCP

Azure

Observability tools

Job description

Grafana Labs, the company behind the open observability cloud, is hiring a Staff-level Backend Engineer to build the first production services for a context layer management system. The role focuses on ingest, storage, retrieval APIs, and agent integrations in a high-autonomy, production-grade environment.

The position is fully remote for candidates in the U.S. or Canada, with a strong emphasis on owning architecture, reliability, and cross-functional collaboration.