Description

You will build and maintain ML deployment pipelines, model monitoring, and inference infrastructure.

This role is on-site.

Responsibilities

• Deploy and manage machine learning models using Docker, REST APIs, and Flask/FastAPI.
• Implement CI/CD pipelines with GitHub Actions and Jenkins for automated model testing and release.
• Orchestrate data pipelines using Spark and Kafka for feature store integration.
• Monitor real-time inference systems and model performance using Prometheus and Grafana.
• Maintain model versioning, experiment tracking, and lifecycle management tools like MLflow or Kubeflow.

Required Skills

• 5+ years of experience in Python programming and software engineering.
• Hands-on experience with Kubernetes for container orchestration and basic deployment.
• Proficiency with MLOps tools: MLflow, Kubeflow, Airflow, SageMaker, or Vertex AI.
• Experience with cloud platforms (AWS, Azure, or GCP) for ML deployment.
• Strong knowledge of CI/CD tools including GitHub Actions and Jenkins.
• Familiarity with LLM deployment, GenAI pipelines, and RAG architectures.
• Experience building real-time inference systems and understanding model monitoring.

Preferred Skills

• Exposure to LLMOps and GenAI deployment pipelines.
• Knowledge of feature stores and data pipeline orchestration.

Key Skills

Education

Any Gradute