Senior AI Observability Engineer

Tealium Inc.; Polska; Hybrid; PLN 290,000 - 375,000; Full time

Benefits offered by this job

Remote-first working

New-hire equity grants

Stipends for home office

Volunteer time off

Job summary

Tealium Inc. is seeking a Senior or Staff Observability/SRE Engineer to implement a robust reliability strategy across customer-facing products, AI features, platform services, and internal systems.

You will own telemetry pipelines, cost controls, and cross-functional collaboration with SRE, MLOps, data engineering, security, and product teams. You will design AI observability for model usage, latency, and cost attribution, leverage OpenTelemetry and tools like Datadog, Prometheus, and Grafana,

Qualifications

• 6+ years in SRE, Observability, or Platform Engineering for 24x7 systems.
• Deep experience with OpenTelemetry and telemetry stacks (Datadog, Prometheus, Grafana).
• Design observability for distributed APIs and event-driven architectures.
• Hands-on with AI/ML/GenAI instrumenting prompts, retrieval, tool use, and evaluation.
• Proficiency with Amazon Bedrock or similar platforms to track model usage, latency, token metrics, and cost attribution.
• Familiarity with agentic workflows, prompt engineering, vector databases (Neptune), RAG architectures, and tools like LangChain, LlamaIndex, or SageMaker.
• Proficiency in Java, Python, or Go.
• Strong AWS expertise, including cloud networking, IAM, security, and quotas.
• Solid IaC, CI/CD, and container experience (Terraform, Kubernetes, Argo CD, Jenkins, GitHub Actions).
• Experience with data modeling, telemetry pipelines, retention, and responsible AI.

Responsibilities

• Lead end-to-end observability design and telemetry pipelines across Tealium products and services.
• Define SLIs/SEOs, error budgets, and production-readiness requirements.
• Architect AI observability for Bedrock, tracking model usage, latency, and costs.
• Establish end-to-end traceability with privacy and security controls.
• Develop dashboards, alerts, and runbooks to enable rapid incident diagnosis.
• Define signals for response quality, groundedness, guardrails, and task completion across AI systems.
• Participate in on-call rotation and drive capacity planning.

Skills

Site Reliability

Observability

Platform Engineering

AI observability

AWS

Java

Python

Go

Cross-functional leadership

Tools

OpenTelemetry

Datadog

Sumo Logic

Prometheus

Grafana

LangChain

LlamaIndex

SageMaker

Neptune

Terraform

Kubernetes

Argo CD

Jenkins

GitHub Actions

Job description

Tealium Inc. is seeking a Senior or Staff Observability/SRE Engineer to implement a robust reliability strategy across customer-facing products, AI features, platform services, and internal systems.

You will own telemetry pipelines, cost controls, and cross-functional collaboration with SRE, MLOps, data engineering, security, and product teams. You will design AI observability for model usage, latency, and cost attribution, leverage OpenTelemetry and tools like Datadog, Prometheus, and Grafana,