MLOps/LLMOps Engineer

• Responsible for operationalizing AI models, ensuring scalable, reliable, and automated deployment of ML and LLM solutions across environments.
• Responsibilities: -

• Build and manage MLOps and LLMOps pipelines
• Automate model deployment using CI/CD pipelines
• Monitor model performance, drift, and retraining cycles
• Manage model serving frameworks (e.g., vLLM, TGI, Ray Serve)
• Implement experiment tracking and model versioning
• Ensure governance, reproducibility, and compliance

• Requirements: -
• Must have minimum 4 years of experience

Experience with Kubernetes, Docker

• CI/CD tools (GitLab, Jenkins, Azure DevOps)
• ML frameworks (TensorFlow, PyTorch)
• Knowledge of LLM serving and optimization