[Remote] Senior AI Engineer | US | Remote

Note: The job is a remote job and is open to candidates in USA. Grafana Labs is a company focused on open observability cloud solutions and is seeking a Senior AI Engineer to lead the AI agent infrastructure and automation platform for their Marketing Operations. The role involves developing multi-agent architectures, integrating LLMs, and building backend services to enhance operational efficiency across various teams.ResponsibilitiesOwn end-to-end development of multi-agent AI systems, from architecture and implementation through testing, deployment, and ongoing operationBuild modular, composable agentic systems using orchestration frameworks (LangChain, CrewAI, Anthropic MCP, or similar) that operate 24/7 across teamsDevelop reusable agentic skills that agents invoke across interfaces (Slack, dashboards, internal apps, CLIs)Implement observability and feedback loops including logging, performance metrics, prompt iteration, model evaluation, and cost managementEstablish governance and compliance standards for AI workflows including access controls, audit trails, PII handling, and human-in-the-loop escalation pathsBuild MCP servers, APIs, CLIs, and microservices connecting AI models to business systems (BigQuery, Slack, CRMs, email, calendars, analytics tools)Architect data flows for retrieval-augmented generation (RAG), connecting LLMs to internal knowledge bases, customer data, and real-time business contextBuild serverless or containerized services (GCP Cloud Functions, Cloud Run) that scale with usage and integrate with Grafana's cloud infrastructurePartner with RevOps, Demand Generation, Regional Marketing, and SDR teams to scope high-impact automation problems, identify bottlenecks, and build solutions with measurable business outcomesDesign and deploy workflows using orchestration tools (n8n, Workato, or custom platforms) with CI/CD, testing, and production reliability standardsBuild systems designed for self-service with documentation, playbooks, and enablement materials that let partner teams operate independentlySkills8+ years of software engineering experience with depth in backend development, systems integration, or data/analytics engineering2+ years hands-on experience applying LLMs/AI to production workflows, not just prototypesStrong proficiency in Python and JavaScript/Node.js with Git-based workflows, code review practices, and testing disciplineHands-on experience with LLM frameworks and patterns including prompt engineering, RAG, function calling/tool use, structured output parsing, and evaluationExperience building and operating multi-agent systems at scale including agent decomposition, orchestration patterns (sequential chains, router/dispatcher, parallel fan-out), state management, and production monitoringYou diagnose business problems before writing code. You think in workflows and outcomes, not just functionsDeep familiarity with Google Cloud Platform, BigQuery, and serverless/containerized services (Cloud Functions, Cloud Run)Understanding of LLM failure modes and production mitigations including confidence thresholds, fallback logic, human escalation, and cost/latency managementProven ability to identify high-leverage problems, push back on low-impact requests, and deliver end-to-end with minimal directionFluent with AI-assisted development tools (GitHub Copilot, Cursor, Claude Code). You use AI to build AI systemsClear technical communicator who can explain complex systems in simple terms to both engineers and business stakeholdersExperience with vector databases or retrieval pipelines (Pinecone, Weaviate, ChromaDB, Qdrant, pgvector)Familiarity with marketing or sales platforms (Salesforce, Customer.io, HubSpot, Marketo, Outreach)Experience with frontend frameworks (React, Slack Block Kit) for building user-facing AI tool interfacesObservability tooling for AI systems (LangSmith, Weights & Biases, custom evaluation frameworks)Experience with workflow orchestration platforms (n8n, Temporal, Prefect, Airflow)Familiarity with Model Context Protocol (MCP) or similar standards for connecting AI systems to data sourcesPrior work automating marketing, sales, or customer success workflows in a B2B SaaS environmentActive in open-source communities. Grafana is built on OSS and we value engineers who share that DNABenefitsAll of our roles include Restricted Stock Units (RSUs), giving every team member ownership in Grafana Labs' success.100% Remote, Global Culture - As a remote-only company, we bring together talent from around the world, united by a culture of collaboration and shared purpose.Scaling Organization – Tackle meaningful work in a high-growth, ever-evolving environment.Transparent Communication – Expect open decision-making and regular company-wide updates.Innovation-Driven – Autonomy and support to ship great work and try new things.Open Source Roots – Built on community-driven values that shape how we work.Empowered Teams – High trust, low ego culture that values outcomes over optics.Career Growth Pathways – Defined opportunities to grow and develop your career.Approachable Leadership – Transparent execs who are involved, visible, and human.Passionate People – Join a team of smart, supportive folks who care deeply about what they do.In-Person onboarding - We want you to thrive from day 1 with your fellow new ‘Grafanistas’ to learn all about what we do and how we do it.Balance is Key - We operate a global annual leave policy of 30 days per annum.3 days of your annual leave entitlement are reserved for Grafana Shutdown Days to allow the team to really disconnect.We will comply with local legislation where applicable.Company OverviewGrafana Labs is an open-source software platform built to support monitoring, visualization, and metric analytics. It was founded in 2014, and is headquartered in New York, New York, USA, with a workforce of 1001-5000 employees. Its website is http://grafana.com.