Position Overview
We're looking for a mid-level DevOps Engineer to join our infrastructure team. You'll build and maintain the systems that power our applications and AI/ML workloads, working at the intersection of traditional infrastructure and emerging AI infrastructure. This is a hands-on role for someone who enjoys automation, reliability, and scaling systems that support data-intensive and GPU-accelerated workloads.
This is a hybrid role requiring at least 3 days in office.
Responsibilities
- Design, deploy, and maintain CI/CD pipelines for application and ML model deployment
- Manage cloud infrastructure (AWS/GCP/Azure) using Infrastructure as Code
- Support AI/ML infrastructure: GPU compute provisioning, model serving, and inference pipelines
- Build and maintain containerized workloads using Docker and Kubernetes
- Implement monitoring, logging, and alerting for system reliability and observability
- Collaborate with ML engineers and data scientists to operationalize models (MLOps)
- Automate infrastructure provisioning and configuration management
- Participate in on-call rotation and incident response
- Optimize infrastructure costs, particularly for compute-heavy AI workloads
Requirements
- 3+ years of DevOps, SRE, or infrastructure engineering experience
- Proficiency with at least one major cloud provider (AWS, GCP, or Azure)
- Strong experience with Infrastructure as Code (Terraform, CloudFormation, or Pulumi)
- Hands-on experience with Docker and Kubernetes
- Solid scripting skills (Python, Bash, or Go)
- Experience building and maintaining CI/CD pipelines (GitLab CI, GitHub Actions, Jenkins, etc.)
- Familiarity with monitoring/observability tools (Prometheus, Grafana, Datadog, etc.)
- Strong understanding of Linux systems and networking fundamentals
Preferred Qualifications
- Experience with GPU infrastructure and CUDA-enabled workloads
- Exposure to ML pipeline and orchestration tools
- Familiarity with model serving frameworks
- Understanding of MLOps practices and model lifecycle management
- Experience with distributed training or large-scale data processing
- Exposure to vector databases or LLM application infrastructure
Completion of a Background Check is required for employment at iCOUNTER
