Staff Backend Engineer - Second Horizon | US | Remote

This is a remote opportunity and we are looking for candidates from the U.S. or Canada. Residents of Quebec are not eligible for this role.

At Grafana Labs, we build observability tools that help users understand, respond to, and improve their systems – regardless of scale, complexity, or tech stack. We recently started a skunkworks initiative with a mission to bring observability to the rest of the business. Our goal is to make Grafana the single best place where humans and AI agents understand and act on real-time data from across the enterprise. As part of this initiative, we are building an AI-native data intelligence system that gives agents reliable, governed access to enterprise context. This system helps agents retrieve the right data, metadata, definitions, lineage, quality signals, and institutional knowledge without every agent builder having to maintain their own brittle context files. The principle is simple: the context system retrieves, agents decide, and data teams maintain the intelligence.

The new team is a mix of seasoned Grafanistas and new hires. We operate with a high degree of autonomy and ownership, both as individuals and as a team. Engineers are empowered to make decisions, move quickly, and validate ideas early – while being supported by a deeply collaborative culture that values curiosity, feedback, and cross-functional partnership.

We’re looking for a Staff-level Backend Engineer to help build the first production services for this context layer management system. You will design and ship the core backend architecture that powers ingestion, context storage, retrieval APIs, and agent-facing integrations. This is an early-stage role on a high-autonomy team, so you should be comfortable working through ambiguity, making pragmatic architectural decisions, and building systems that can evolve from internal dogfooding to production-grade SaaS. As the team matures, there’s a broad opportunity to expand or redefine this role based on impact and initiative.

Key responsibilities:

• Build the core backend services: Design, implement, test, and operate the first services for context ingestion, context indexing, retrieval orchestration, API access, source configuration, and system administration.
• Create a scalable SaaS foundation: Help define and build the architecture for a multi-tenant service, including tenant isolation, usage tracking, quotas, audit logs, background jobs, and reliable service boundaries.
• Power agent-facing retrieval workflows: Build APIs and service interfaces that allow AI agents, MCP tools, CLIs, and internal applications to retrieve relevant context, provenance, confidence signals, and warnings.
• Work across product and infrastructure: Partner with the team to make practical tradeoffs between fast experimentation and long-term reliability, especially as the project moves from prototype to production.
• Operate what you build: Instrument services with metrics, logs, traces, alerts, and dashboards. Use observability tools to understand system behavior and improve reliability.
• Contribute to technical direction: Help shape the architecture, service boundaries, storage choices, API contracts, deployment patterns, and engineering practices for a new product area.
• Effective communication: You’ll be working in a highly dynamic and collaborative environment, so we need someone who can communicate effectively and contribute across teams.
• Ownership and impact: Take full ownership of the AI solutions you develop, ensuring they are not only innovative but also scalable, maintainable, and aligned with real user workflows. 

What we're looking for:

• Strong engineering skills: Solid experience building production-grade, user-facing software systems. You’re a self-starter, capable of tackling complex engineering problems and making UI design decisions with minimal supervision.
• AI experience with a practical mindset: You’re familiar with AI technologies and frameworks, and you focus on delivering high-quality solutions that work in the real world, not just in theory. 
• Quick iteration and experimentation: You’re comfortable releasing prototypes, collecting feedback, and iterating with a pragmatic mindset.
• Proven initiative: You take ownership and drive projects forward, pushing boundaries to find the most impactful solutions. You can deal with ambiguity and are able to define scope where things are loosely defined. 
• Collaborative attitude: You communicate effectively with your peers. You’re open to feedback, and you bring a solutions-oriented mindset to the table.

Requirements:

• Experience with LLMs, prompt engineering, and building applications powered by GenAI.
• Proven track record of delivering software that made it into production and is actively used by users. 
• Exposure to working in cloud-native environments (e.g., AWS, GCP, Azure).
• Experience using observability tools to understand and troubleshoot system behavior.

Nice to have:

• Experience building or working with agent frameworks or multi‑agent workflows.
• Experience as a data analyst or work with data platforms (e.g., Looker, Tableau, PowerBI, Snowflake, DataBricks)
• Experience building tools for data engineering. 

In the US, the Base compensation range for this role is $174,986 - $209,983.  Actual compensation may vary based on level, experience, and skillset as assessed in the interview process. Benefits include equity, bonus (if applicable) and other benefits listed here.

#LI-Remote