DevOps Engineer

Akkadian Labs•Hoboken, NJ

5h•Remote

About The Position

Akkadian Labs is seeking a DevOps Engineer to support the design, implementation, and maintenance of scalable and secure infrastructure and DevOps processes. This role involves working with development, QA, and product teams to ensure reliable deployments, automate workflows, and enhance system observability across Rocky OS-based, AWS-hosted, and on-premises solutions. It is a hands-on technical position focused on execution, continuous improvement, and operational excellence within the DevOps function, reporting to the DevOps Manager.

Requirements

5+ years of experience in DevOps, Site Reliability Engineering (SRE), or a related role.
Hands-on experience with AWS (e.g., EC2, ECS, S3, IAM, Lambda, CloudWatch).
Working knowledge of Linux environments.
Familiarity with Docker and Kubernetes.
Basic to intermediate scripting ability in Python, Bash, or similar languages.
Experience building or maintaining CI/CD pipelines and related tools.
Exposure to monitoring and observability tools such as Prometheus, Grafana, and ELK.
Understanding of secure DevOps practices and basic compliance concepts.

Nice To Haves

Experience supporting AI or machine learning workloads, compute environments.
Exposure to AI model deployment pipelines and model versioning practices.
Experience with infrastructure-as-code tools such as Terraform or CloudFormation.
Familiarity with hybrid cloud or on-premises environments.
Exposure to security best practices in DevOps contexts, including AI-specific concerns such as data isolation and access controls.
Experience supporting production systems and participating in on-call rotations.

Responsibilities

Support deployment and maintenance of scalable infrastructure in AWS and hybrid cloud environments.
Assist in managing infrastructure-as-code (IaC) using Terraform, CloudFormation, or similar tools.
Help maintain Linux-based environments.
Contribute to containerization efforts using Docker and orchestration via Kubernetes.
Work on the design, deployment and management of AI agent workloads, including provisioning compute instances and managing resource scaling for inference-heavy tasks.
Play a key role in building and maintaining model deployment pipelines, including versioning, testing, and rollback of AI models in production environments.
Monitor AI API consumption and infrastructure costs, implementing alerting and controls to prevent runaway usage and support budget visibility.
Coordinate the implementation of infrastructure-level security guardrails for AI systems, including access controls and data isolation for model inputs and outputs.
Manage monitoring and observability efforts using tools such as Prometheus, Grafana, and the ELK stack.
Troubleshoot system issues and contribute to incident response and root cause analysis.
Develop and execute strategies for improving system reliability, performance, and uptime.
Build, maintain, and optimize CI/CD pipelines using tools such as Jenkins, BitBucket CI/CD, or similar.
Automate routine operational tasks including builds, testing, deployments, and system updates.
Work with engineering teams to integrate pipelines with Akkadian tools.
Follow secure DevOps practices and assist in implementing security controls.
Support compliance initiatives and vulnerability remediation efforts.
Work closely with DevOps, engineering, QA, and product teams to support deployments and releases.
Maintain documentation for infrastructure, processes, and operational procedures.
Participate in team ceremonies and continuous improvement initiatives.