DevOps Engineer (AI & Infrastructure)

Key Responsibilities

• Containerization & Orchestration: Dockerize AI code and build microservice architectures. Manage, scale, and orchestrate container clusters using Kubernetes.

• AI Model Optimization: Work alongside data scientists to optimize AI models for production performance (speed, memory, and resource usage).

• Module Implementation: Deploy and integrate AI models, alongside their respective pre-processing and post-processing pipelines

• CI/CD Automation: Develop, maintain, and optimize CI/CD pipelines to enable smooth integration, testing, and continuous delivery of AI workloads.

• Platform Reliability: Monitor system metrics, proactively troubleshoot production issues, and scale infrastructure to meet varying AI workload demands.

Must-Have Qualifications & Skills

• Experience: 3+ years in DevOps, Cloud Engineering, or related system administration roles.

• Containerization: 3 to 5 years of dedicated, hands-on experience with Docker and image optimization.

• Orchestration: 3 to 5 years of proven experience managing and scaling Kubernetes clusters in production environments.

• Programming/Scripting: Proficiency in Python or Bash for automation and scripting tasks.

• AI/ML Familiarity: Basic understanding of AI/ML model lifecycles, data pipelines, and hardware acceleration (e.g., GPU management).

Preferred Qualifications

• Experience working with MLOps frameworks or deploying machine learning models.

• Familiarity with cloud platforms (AWS, GCP, or Azure).

• Strong knowledge of observability tools (Prometheus, Grafana, ELK stack)