Назад
Company hidden
9 дней назад

Staff Observability Engineer (AI)

290 000 - 375 000PLN
Формат работы
remote (только Poland)
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Poland
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Staff Observability Engineer (AI): Designing observability strategy, telemetry pipelines, and reliability solutions for customer-facing products, platform services, data pipelines, and AI-powered systems with an accent on OpenTelemetry, Amazon Bedrock, and end-to-end tracing. Focus on measuring AI quality and cost, building SLOs and operational tooling, and solving reliability challenges across distributed and agentic workflows.

Location: Remote Poland

Base salary: 290,000–375,000 PLN annually, with potential performance-based bonus and equity options.

Company

hirify.global provides a real-time Customer Data Platform that helps organizations unify customer data and support personalized, privacy-conscious experiences and enterprise AI strategies.

What you will do

  • Lead observability design, telemetry schemas, and OpenTelemetry pipeline architectures across products, platform services, data pipelines, and internal tools.
  • Define service-level indicators, objectives, error budgets, and production-readiness requirements with engineering and product teams.
  • Architect AI observability for Amazon Bedrock and agentic workflows, including model selection, latency, retries, token usage, tool execution, and cost attribution.
  • Establish traceability across user requests, prompts, model calls, retrieved context, downstream services, and final responses while maintaining privacy and security controls.
  • Build dashboards, alerts, SLOs, runbooks, and operational views for incident diagnosis, performance optimization, and cost control.
  • Participate in an on-call rotation of approximately 20% and lead failure injection, production testing, and capacity planning.

Requirements

  • 6+ years of experience in Site Reliability, Observability, or Platform Engineering supporting 24x7x365 production systems.
  • Deep experience with OpenTelemetry and observability platforms such as Datadog, Sumo Logic, Prometheus, or Grafana.
  • Experience with distributed systems, APIs, event-driven architectures, asynchronous workflows, and AI/ML or GenAI instrumentation.
  • Experience with Amazon Bedrock or similar platforms, including model usage, latency, throttling, token metrics, and cost attribution.
  • Proficiency in Java, Python, or Go, plus strong AWS expertise covering networking, IAM, security, and service quotas.
  • Experience with IaC, CI/CD, containers, data modeling, telemetry pipelines, cardinality management, retention, responsible AI, and data privacy controls.

Nice to have

  • Familiarity with agentic workflows, prompt engineering, vector databases such as Neptune, RAG architectures, LangChain, LlamaIndex, or SageMaker.

Culture & Benefits

  • Remote-first working with support for a home office setup.
  • Paid time off, extended paid parental leave, and company holidays.
  • Health and wellness programs and competitive benefits.
  • Professional development through on-demand courses and leadership programs.
  • Volunteer support with 15 hours of paid work time annually.
  • New hire equity grants and opportunities to participate in hirify.global's ownership program.

Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →