Observability engineer for AI agents

EPAM; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Гибридная/удаленная работа

Relocation opportunities

Сертификации (GCP/Azure/AWS)

Бесплатные курсы английского

Офисы в 55+ странах

Job summary

EPAM ищет старшего инженера Observability, который возьмет на себя владение многоарендной слоем консолидации New Relic и управлением телеметрией для обширной экосистемы агентов. Кандидат должен иметь 5+ лет опыта наблюдаемости/SRE, знать New Relic на масштабе, NRQL, Terraform и Crossplane, а также владеть английским на уровне B2+.

В должности ожидается взаимодействие с командами и развитие общих практик наблюдаемости.

Qualifications

• 5+ лет опыта в observability или SRE-инженерии.
• Опыт консолидации observability для AI агентной инфраструктуры.
• Экспертиза администрирования New Relic на масштабе и настройке cross-account.
• Знания NRQL и разработки dashboards- и alert-policy-кода (Terraform, Crossplane).

Responsibilities

• Управлять многоарендным слоем New Relic и агрегацию телеметрии.
• Собирать телеметрию через NRQL и кросс-аккаунты.
• Разрабатывать dashboards-код и alert-policy-код (Terraform, Crossplane).
• Настраивать политики оповещений в Opsgenie с плановой миграцией в ServiceNow.
• Работать с OpenTelemetry/ADOT и потоками OTLP/Firehose.
• Проектировать размерности метрик для больших агентов и поддерживать секционирование observability.

Skills

Observability engineering

SRE experience

New Relic administration

NRQL queries

Dashboards-as-code

Terraform

Crossplane

Opsgenie familiarity

ServiceNow familiarity

OpenTelemetry

ADOT

English (B2+)

Tools

New Relic

NRQL

Terraform

Crossplane

OpenTelemetry

ADOT

Opsgenie

ServiceNow

Job description

Описание

We are looking for a Senior Observability Engineer to take ownership of the multi-tenant New Relic consolidation layer aggregating telemetry across our agent estate, within an Enterprise Agent Development Platform empowering engineering teams to define, orchestrate, deploy, and observe AI agents at scale across the organization.

Задачи

• Own and administer the multi-tenant New Relic consolidation layer across the agent estate
• Aggregate telemetry from multiple project tenants through cross-account NRQL queries
• Build and maintain dashboards-as-code and alert-policy-as-code with Terraform and Crossplane
• Set up New Relic alert policies routed to Opsgenie, with planned migration to ServiceNow
• Manage OpenTelemetry / ADOT ingestion into New Relic through OTLP and Firehose pipelines
• Design metric dimensions and low-cardinality facets for large-scale agent estates
• Establish cross-account and cross-tenant telemetry aggregation and reporting workflows
• Maintain separation across Technical, Business, and Audit observability models
• Partner with engineering teams to standardize agent observability practices across the platform

Требования

• 5+ years of experience in observability or SRE engineering
• Hands-on experience consolidating observability/telemetry for AI agent estates within a production agentic AI project, such as multi-tenant New Relic aggregation, cost/token attribution for GenAI workloads, or AgentCore GenAI Observability integration
• Expertise in New Relic administration at scale, covering management account setup and cross-account configuration
• Proficiency in NRQL for cross-account queries aggregating telemetry from multiple project tenants
• Skills in dashboards-as-code and alert-policy-as-code with Terraform New Relic provider and Crossplane
• Knowledge of New Relic alert policies routed to Opsgenie, along with familiarity with ServiceNow
• Understanding of OpenTelemetry / ADOT consumption fundamentals, covering OTLP and Firehose ingestion into New Relic
• Competency in metric dimension design for large agent estates, ensuring stable, low-cardinality facets
• Background in running New Relic or equivalent SaaS observability platforms as a multi-tenant consolidation layer
• Experience operating within a Technical / Business / Audit observability segregation model
• English proficiency at an Upper-Intermediate level (B2) or higher

Будет плюсом

• Familiarity with AWS Bedrock AgentCore observability, covering Transaction Search and GenAI Observability;
• Understanding of Kinesis Firehose metric and log forwarding pipelines from CloudWatch into New Relic;
• Expertise in cost/token attribution modeling for GenAI workloads;
• Knowledge of Crossplane-based provisioning of observability resources

Условия

Delivering innovative solutions to industry leaders, making a global impact Enjoyable working environment, whether it is the vibrant office or the comfort of your own home Opportunity to work abroad for up to two months per year Relocation opportunities within our offices in 55+ countries Corporate and social events Leadership development, career advising, soft skills and well-being programs Certifications, including GCP, Azure and AWS Unlimited access to EPAM's internal learning database Free English classes with certified teachers Discounts in local language schools, including offline courses for the Uzbek language Monetary bonuses for engaging in the referral program Medical & family care package Four trust days per year (sick leave without a medical certificate) Discounts for fitness clubs, dance schools and sports programs Benefits package (sports activities, a variety of stores and services)