Observability engineer for GenAI and compute

We are looking for an Observability Engineer to design and implement consolidated observability dashboards and cost metrics across a GenAI and compute environment. The role focuses on New Relic dashboarding, NRQL, cost and token-usage visibility, and transforming raw telemetry into governed, reusable aggregate metrics that provide both technical and business insights.

• Build and maintain New Relic dashboards using NRQL queries.
• Develop consolidated cross-tenant dashboards providing visibility into agent health, costs, and the overall estate.
• Implement cost and token-usage metrics for GenAI and compute workloads.
• Transform raw telemetry into governed, reusable aggregate metrics, ensuring appropriate lineage rather than simply replicating raw data.
• Define and maintain separation between technical and business observability, including metric derivation, replication, and linkage.
• Ensure strong metric facet hygiene, with consistent and low-cardinality dimensions.
• Support integration of observability metrics with downstream BI and analytics products where required.
• Contribute to ingestion and integration patterns using New Relic Metric API / Firehose and AWS cost-allocation data.

• New Relic dashboard building and NRQL queries
• Consolidated cross-tenant dashboards for agent health, cost, and estate overview
• Cost and token usage metrics for GenAI and compute workloads
• Deriving governed aggregate metrics from raw telemetry (with lineage, not raw copies)
• Technical vs Business observability segregation (derivation, replication, linkage)
• Metric facet hygiene (consistent, low-cardinality dimensions)
• 4+ years of observability engineering
• Dashboard and cost-metric implementation on New Relic (or equivalent SaaS observability)
• Translating raw telemetry into governed, reusable aggregate metrics
• Будет плюсом: New Relic Metric API / Firehose ingestion familiarity; AWS cost allocation (Cost Explorer, tagging, per-account attribution); OpenTelemetry GenAI semantic conventions (gen_ai. , project. Agent*.*); Feeding a downstream BI/analytics data product

• That’s why we offer a range of benefits that support your well-being and charge your professional growth.