Devops Engineer (Remote)

Job Overview:

We are seeking a highly skilled and motivated DevOps Engineer to join our dynamic team. The ideal candidate will have experience in designing, building, and managing CI/CD pipelines, deploying machine learning models, and troubleshooting Advanced knowledge of Triton Inference Server, TensorRT, and ONNX Runtime, Kubernetes environments. You will collaborate closely with machine learning engineers to ensure smooth deployment, scalability, and optimal performance of microservices and ML models.

Key Responsibilities:

• CI/CD Pipeline Design & Maintenance: Build and manage continuous integration/continuous deployment (CI/CD) pipelines on Jenkins to automate the deployment of microservices on Google Kubernetes Engine (GKE).

• Kubernetes Management: Deploy, monitor, and troubleshoot Kubernetes (K8s) clusters and pods. Address issues such as pod failures and optimize cluster performance.

• Microservices Deployment: Manage the containerization and deployment of microservices using Docker and Kubernetes, ensuring smooth scalability and high availability.

• Model Deployment & Optimization: Collaborate with ML engineers to understand and deploy machine learning models, leveraging GPU resources to reduce latency and improve performance. Implement strategies to enhance the efficiency of model serving.

• Monitoring & Logging: Implement and maintain monitoring solutions using tools like Prometheus, Grafana, and ELK Stack to ensure system performance, reliability, and to respond to any incidents proactively.

• Version Control & Code Management: Work with Git for version control, ensuring robust branching strategies and codebase integrity.

• Collaboration & Communication: Work closely with cross-functional teams, including developers, machine learning engineers, and operations teams to ensure smooth development, deployment, and scaling of applications.

Required Skills:

• Experience with deploying machine learning models
• Experience with Jenkins for CI/CD pipeline automation.
• Proficiency in Kubernetes for managing containerized applications.
• Knowledge of Docker for containerization.
• Advanced knowledge of Triton Inference Server, TensorRT, and ONNX Runtime for ML model optimization and deployment.
• Experience with Google Kubernetes Engine (GKE) for deploying and scaling microservices.
• Understanding of GPU optimization for deploying machine learning models.
• Expertise in Linux (Ubuntu) for server management and troubleshooting.
• Grasp of Git for source control and collaboration.
• Familiarity with cloud platforms (e.g., GCP, AWS, or Azure) for scalable deployments.

Nice to Have:

• Familiarity with Ray Serve for model deployment and scaling.
• Knowledge of ML model serving frameworks and tools like TensorFlow Serving, FastAPI, or Ray.
• Experience with security best practices in CI/CD and containerized environments.
• Exposure to cloud-based machine learning pipelines.
• Knowledge of monitoring tools (e.g., Prometheus, Grafana) and logging systems (ELK stack).