GenAI Ops Engineer — Scalable AI Infra, Remote Options

EPAM Systems; Poland; Hybrid; PLN 180,000 - 300,000; Full time

Benefits offered by this job

Hybrid work model

Remote within Poland

Relocation opportunities

Employee stock purchase plan

Health insurance

English language courses

Job summary

EPAM Systems seeks a GenAI Ops Engineer to build, deploy, and maintain GenAI infrastructure across major clouds. You will work with data scientists, ML engineers, and developers to scale and secure complex AI services.

You will design and manage CI/CD pipelines, implement Terraform-based IaC, and monitor model performance. Experience with multi-agent systems, LLM inference, and tool integration is highly valued. Hybrid/remote options available within Poland.

Qualifications

• 3+ years in a DevOps/SRE/MLOps role with cloud focus.
• Experience building and managing CI/CD pipelines and scripting (Python/Bash).
• Familiarity with IaC tools (Terraform, AWS CDK/CloudFormation) and containerization (Docker/Kubernetes).
• Track record deploying and operating LLM inference.
• Experience with tracing/metrics and evaluation pipelines (OpenTelemetry, Langfuse).
• Experience with retrieval pipelines and vector DBs (Pinecone, Weaviate, Milvus, FAISS).
• Experience running multi-agent workflows and state management.
• Experience implementing guardrails and security practices.

Responsibilities

• Build and manage CI/CD pipelines for training, evaluating, and deploying GenAI models.
• Orchestrate multi-agent AI workflows with A2A communication and coordination.
• Manage tool integration between AI agents and external APIs using MCP standards.
• Leverage AI-powered tools to accelerate the entire development lifecycle.
• Define and manage GenAI infrastructure via IaC (Terraform, cloud-native tools).
• Implement comprehensive model monitoring and observability for health and cost.
• Design scalable architectures for model serving and inference performance.
• Ensure security, compliance, and data protection across GenAI systems.

Skills

CI/CD pipelines

Cloud platforms

Multi-agent workflows

LangGraph/CrewAI

Tools

Terraform

Docker

Kubernetes

AWS CDK

CloudFormation

KServe/Seldon

Job description

EPAM Systems seeks a GenAI Ops Engineer to build, deploy, and maintain GenAI infrastructure across major clouds. You will work with data scientists, ML engineers, and developers to scale and secure complex AI services.

You will design and manage CI/CD pipelines, implement Terraform-based IaC, and monitor model performance. Experience with multi-agent systems, LLM inference, and tool integration is highly valued. Hybrid/remote options available within Poland.