Machine Learning Engineer

Iitjobs Inc.; Mumbai; Hybrid; INR 1,500,000 - 2,100,000; Full time

Job summary

Iitjobs Inc. in Mumbai is seeking an experienced ML/MLOps Engineer to migrate Python-based ML models from Azure VM to a Databricks + MLflow architecture, and to convert data processing logic to PySpark for scalable processing.

You will implement end-to-end MLOps practices, configure MLflow, design a Feature Store, collaborate with data science leads, and run pilot migrations of 2-3 models while ensuring production baselines remain intact.

Qualifications

• Analyze and migrate Python-based ML models from Azure VM environments to a Databricks and MLflow-based architecture.
• Convert existing Python data processing and model execution logic to PySpark for scalable distributed processing.
• Implement MLOps best practices including model versioning, experiment tracking, CI/CD integration, deployment automation, and governance.
• Configure and manage MLflow for model lifecycle management, tracking, registration, and deployment.
• Design and establish Feature Store capabilities to support reusable and governed machine learning features.
• Collaborate with Data Science Leads and domain experts to understand existing model logic, dependencies, and business objectives.

Responsibilities

• Analyze and migrate Python-based ML models from Azure VM environments to a Databricks and MLflow-based architecture.
• Convert existing Python data processing and model execution logic to PySpark for scalable distributed processing.
• Implement MLOps best practices including model versioning, experiment tracking, CI/CD integration, deployment automation, and governance.
• Configure and manage MLflow for model lifecycle management, tracking, registration, and deployment.
• Design and establish Feature Store capabilities to support reusable and governed machine learning features.
• Collaborate with Data Science Leads and domain experts to understand existing model logic, dependencies, and business objectives.
• Execute pilot migration of 2-3 critical ML models and create a scalable framework for the remaining models.
• Validate migrated models by performing data quality checks, drift analysis, and output consistency testing.
• Ensure model performance remains aligned with existing production baselines during migration.
• Develop reusable code accelerators, migration templates, and deployment standards.
• Implement batch deployment mechanisms and monitoring processes for production workloads.
• Document architecture, migration strategy, testing results, and operational procedures.

Skills

Databricks MLflow Migration

Python & PySpark Development

Azure Databricks Batch Deployment

Feature Store

Data Validation & Drift Monitoring

MLOps Implementation & Model Lifecycle

Job description

Ideal Candidate

• 3-5 years of experience in Machine Learning Engineering, Data Engineering, or MLOps.
• Strong development experience using Python and machine learning libraries.
• Hands-on experience with Databricks, PySpark, and distributed data processing.
• Experience implementing MLflow and MLOps frameworks in enterprise environments.
• Good understanding of Azure cloud services and model deployment architectures.
• Familiarity with feature engineering, feature stores, model governance, and experiment tracking.
• Knowledge of model validation, monitoring, data drift detection, and model performance management.
• Exposure to CI/CD pipelines for machine learning workloads.
• Strong analytical and problem-solving skills with the ability to work directly with business and domain experts.
• Comfortable working from the Mumbai office in a collaborative, fast-paced environment.

Roles and Responsibilities

• Analyze and migrate Python-based ML models from Azure VM environments to a Databricks and MLflow-based architecture.
• Convert existing Python data processing and model execution logic to PySpark for scalable distributed processing.
• Implement MLOps best practices including model versioning, experiment tracking, CI/CD integration, deployment automation, and governance.
• Configure and manage MLflow for model lifecycle management, tracking, registration, and deployment.
• Design and establish Feature Store capabilities to support reusable and governed machine learning features.
• Collaborate with Data Science Leads and domain experts to understand existing model logic, dependencies, and business objectives.
• Execute pilot migration of 2-3 critical ML models and create a scalable framework for the remaining models.
• Validate migrated models by performing data quality checks, drift analysis, and output consistency testing.
• Ensure model performance remains aligned with existing production baselines during migration.
• Develop reusable code accelerators, migration templates, and deployment standards.
• Implement batch deployment mechanisms and monitoring processes for production workloads.
• Document architecture, migration strategy, testing results, and operational procedures.

Mandatory Skills

• Databricks MLflow Migration
• Python & PySpark Development
• Azure Databricks Batch Deployment
• Feature Store
• Data Validation & Drift Monitoring
• MLOps Implementation & Model Lifecycle Management