DevOps engineer for AI agent platforms

EPAM; United States; Hybrid; USD 140,000 - 190,000; Full time

Benefits offered by this job

Office or home-friendly environment

Global mobility opportunities

Comprehensive learning resources

Job summary

EPAM is seeking a Senior DevOps Engineer to help build an Enterprise Agent Development Platform—a cloud-native ecosystem enabling engineering teams to define, orchestrate, deploy, and observe AI agents at scale on AWS AgentCore Runtime.

You will own the agent CI/CD pipeline, integrate security scans, manage registry versioning, and collaborate with platform, ML, and security teams to enforce quality and release standards across all agent deployments.

Qualifications

• 3+ years of DevOps or platform engineering with AI/ML pipelines.
• Hands-on experience building CI/CD for AI agents in production.
• Experience with ARM64 agent builds, security scans, and registry versioning.
• Proficiency in GitHub Actions for agent workflows.

Responsibilities

• Build and operate the agent CI/CD pipeline end-to-end.
• Manage AWS ECR and tagging strategies for agent images.
• Design and maintain agent registry integration with metadata.
• Implement GitHub Actions workflows for matrix builds and scans.
• Collaborate with platform, ML, and security teams on quality and release standards.

Skills

CI/CD for AI agents

GitHub Actions

Docker

AWS ECR

Security scanning in CI/CD

LangGraph/LangChain

ARM64 agent builds

Tools

Docker

GitHub Actions

AWS ECR

LangGraph

LangChain

Job description

Описание

We are seeking a Senior DevOps Engineer to help build an Enterprise Agent Development Platform — a production-grade, cloud-native ecosystem that enables engineering teams to define, orchestrate, deploy, and observe AI agents at scale. The platform standardizes agent development across the organization using LangGraph and Strands Agents on AWS AgentCore Runtime.

Задачи

Build and operate the agent CI/CD pipeline, including ARM64 agent container builds, security scanning, pushing to ECR, and triggering AgentCore Runtime version creation Design and maintain Agent Registry integration to auto-register agent versions with metadata such as git SHA, evaluation pass/fail status, and promotion status Implement GitHub Actions workflows for agent-specific use cases, including matrix builds and specialized security scans (prompt injection, PII leakage) Manage AWS ECR for agent images with semantic versioning tags and git SHA tags for full traceability Define and evolve the agent version metadata schema, covering version ID, container digest, timestamp, evaluation results, and tool/policy bindings Integrate security scanning across the pipeline for vulnerabilities, secrets, and compliance checks Establish container registry management practices and tagging strategies to support reliable agent delivery Partner with platform, ML, and security teams to enforce consistent quality, governance, and release standards across all agent deployments

Требования

3+ years of experience in DevOps or platform engineering with AI/ML pipelines Hands-on background in building CI/CD pipelines specifically for AI agents in a production agentic AI project — e.g., ARM64 agent container builds with security scanning, AWS AgentCore Runtime version registration, or agent-specific evaluation-gate integration in GitHub Actions (generic containerized CI/CD experience without agent/AgentCore context does not meet this bar) Proficiency in CI/CD pipeline implementation for containerized AI agents or ML models Expertise in container registry management, tagging strategies, and AWS ECR for agent images with semantic and git SHA versioning Skills in security scanning within CI/CD workflows, covering vulnerabilities, secrets, and compliance Competency in GitHub Actions for agent workflows, including matrix builds and agent-specific scans for prompt injection and PII leakage Understanding of agent version metadata schemas, including container digests, evaluation results, and tool/policy bindings Familiarity with Docker for building and operating containerized agent workloads English proficiency at an Upper-Intermediate level (B2) or higher Будет плюсом: Knowledge of AWS AgentCore Runtime endpoint management API; Background in agent evaluation gate integration to block promotion when evaluations fail; Familiarity with GitOps promotion patterns for agents; Skills in LangChain/LangGraph agent packaging and deployment

Условия

Enjoyable working environment, whether it is the vibrant office or the comfort of your 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 Participation in the Employee Stock Purchase Plan Monetary bonuses for engaging in the referral program Comprehensive medical & family care package Four trust days per year for personal needs Discounts for fitness clubs Benefits package (hotels, restaurants, stores and services)