Machine Learning Engineer

About the Role

The Machine Learning Developer will be responsible for designing, developing, and maintaining scalable machine learning models and data pipelines that support key business use cases. This is a hands-on role requiring strong expertise in Python for model development, feature engineering, and pipeline automation, with extensive use of Azure ML and Azure DevOps.

Success in this role will be measured by the delivery of reliable, production-ready models that demonstrate clear business impact, maintain traceable data lineage, and operate efficiently at scale with high standards of operational excellence.

Responsibilities

Feature Engineering & Model Development

• Convert data science prototypes into production-grade Azure ML pipelines, including data ingestion, model training, inference, and automated retraining.
• Design, build, and refine machine learning models for forecasting, classification, and regression using frameworks such as scikit-learn, XGBoost, LightGBM, PyTorch, and TensorFlow.
• Develop robust, reusable feature pipelines using Pandas and PySpark, ensuring deterministic logic and modular design, and orchestrate them using Azure ML Pipeline Jobs.
• Plan and execute experiments with appropriate sampling strategies, train-test splits, cross-validation techniques, and performance metrics (e.g., RMSE, AUC, MAPE).
• Implement model lifecycle strategies including versioning, champion/challenger comparisons, and promotion mechanisms.
• Maintain comprehensive documentation of experiments to support reproducibility and regulatory or audit requirements.

Model Deployment, Operations & Monitoring

• Deploy models as batch or real-time inference endpoints using Azure ML.
• Implement validation checks for model performance, data drift, prediction distribution shifts, and champion versus challenger evaluations.
• Create and maintain monitoring dashboards to track latency, prediction freshness, data drift, and feature importance.
• Integrate model testing and deployment workflows into Azure DevOps CI/CD pipelines.
• Develop and maintain FastAPI-based services to expose and consume machine learning models.

Data Engineering & Quality Management

• Ingest, profile, clean, and transform data from Snowflake, SQL databases, and third-party data sources.
• Implement robust data quality checks including null handling, schema validation, outlier detection, time alignment, and duplicate detection.
• Automate feature extraction processes and ensure consistency across feature stores.

Collaboration & Quality Operations

• Collaborate closely with Product, Data, and QA teams to define model acceptance criteria and conduct structured experiment reviews.
• Contribute to defect classification frameworks covering data, model, and serving issues.
• Support pipeline observability initiatives and help maintain service-level objective (SLO) dashboards.

Qualifications

• Minimum 5 years of experience building data-driven solutions, with at least 3 years focused on machine learning modelling and operations.
• Strong proficiency in Python (including pandas, NumPy, and ML frameworks), SQL, and cloud-based data tools.
• Proven experience developing and managing production machine learning pipelines using Azure ML, Databricks, or similar platforms.
• Solid understanding of model validation techniques, drift detection, and real-time or batch monitoring.
• Hands-on experience with feature stores, CI/CD pipelines (Azure DevOps), and API development using FastAPI or Flask.
• Bachelor's or Master's degree in Computer Science, Statistics, Information Technology, or a related discipline.
• Azure Data Engineer or Azure Machine Learning Engineer Associate certification is an added advantage.