Senior Software Engineer (Observability Insights)

We are seeking senior engineers to lead our Observability Insights effort, building the product experiences and agentic interfaces that sit on top of our foundational telemetry layer.

You will play a pivotal role in enabling CoreWeave and its customers to understand, troubleshoot, and optimize complex AI systems by delivering core building blocks like multi-tenant APIs, managed Grafana experiences, and MCP-based tool servers.

You’ll collaborate closely with PMs and engineering leadership to shape the end-to-end observability experience, providing an outsize opportunity to influence how the world interacts with the forefront of Artificial Intelligence

Design and execute the development of highly available, multi-tenant APIs that expose telemetry and derived insights in an developer obsessed way

Modernize how users interact with data by building agentic experiences, including MCP servers, agentic tools and API gateways that safely expose foundational telemetry

Build agentic observability capabilities that will enable agentic workflows for guided debugging, workload optimization, and incident summarization to empower CoreWeavers and customers alike

Develop and enforce best practices regarding the health of telemetry data pipelines, specifically focused on correlation primitives and aggregation services for RCA and performance detection

Improve the performance, security, reliability, and scalability of insights services including SLO ownership and latency optimization while participating in the team’s on-call rotation

Collaborate closely with internal engineering teams, applying a platform-as-a-product mindset to understand their needs and embed observability best practices and custom tooling into their systems

Contribute to the overall observability strategy, influencing the direction of our platform- Experienced in agentic applications or LLM-based features, including grounding, tool calling, and operational safety

Familiar with observability systems such as ClickHouse, Loki, VictoriaMetrics, Prometheus, and Grafana

Strong focus on developer-facing infrastructure, with a customer-obsessed approach to SDKs, CLIs, and APIs

6+ years of experience in software or infrastructure engineering building production-grade backend systems and distributed APIs

Comfortable writing production code primarily in Go, with the ability to integrate Python components when needed

Collaborative experience in agile teams delivering end-to-end telemetry-to-insights pipelines

Proficient in reliability engineering, including fault-tolerant design, SLOs, error budgets, and multi-tenant system resilience

Wondering if you’re a good fit? We believe in investing in our people, and value candidates who can bring their own diversified experiences to our teams – even if you aren’t a 100% skill or experience match. Here are a few qualities we’ve found compatible with our team. If some of this describes you, we’d love to talk

You love transforming complex telemetry into actionable insights

You’re curious about agentic interfaces and the future of AI observability

You’re an expert in building scalable, reliable systems that empower developers and customers alike

Hands-on experience with logging, tracing, and metrics platforms in production, with deep knowledge of cardinality, indexing, and query optimization

Experience operating Kubernetes clusters at scale, especially for AI workloads

Experienced in running distributed systems or API services at cloud scale, including event streaming and data pipeline management

Familiarity with LLM frameworks, MCP, and agentic tooling (e.g., Langchain, AgentCore)