Data Scientist

SiteMinder; Pune District; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

SiteMinder is seeking a Data Scientist to design and deploy end-to-end ML solutions that drive product intelligence and business impact. You will work with Principal Data Scientists and the Core Data Lab to productionize models, collaborate with engineering, and build scalable pipelines using Databricks, PySpark, and Delta Lake.

You will monitor models, address drift, and contribute to feature stores while staying current with ML trends.

Qualifications

• Hands-on experience applying ML in production or product environments.
• Strong understanding of ML techniques from traditional models to deep learning.
• Experience building scalable ML pipelines and automating workflows with MLOps tools.
• Proficiency in Python and libraries like Scikit-learn, PyTorch, TensorFlow, and PySpark.

Responsibilities

• Design and develop end-to-end ML solutions from data exploration to deployment.
• Collaborate cross-functionally with engineers, analysts, and product teams to integrate models.
• Implement scalable ML pipelines using Databricks, PySpark, and Delta Lake.
• Operationalize models with CI/CD and MLOps practices; monitor for drift and performance.
• Contribute to feature stores and reusable data assets for faster experimentation.

Skills

ML modelling

MLOps

Python

SQL

Feature engineering

Tools

Databricks

PySpark

Delta Lake

MLflow

Kubeflow

Sagemaker

Bedrock

Job description

As a Data Scientist, you will play a pivotal role in building and scaling machine learning

solutions that drive product intelligence and data-informed decision-making across

SiteMinder. You will work closely with Principal Data Scientists and the Core Data Lab team

to develop, validate, and productionise models that deliver real business impact. In

collaboration with Engineering, you will focus on integrating models into products and

tackling complex data science challenges related to prediction, recommendation, and

What you’ll do…

• Design and develop end-to-end ML solutions — from data exploration and feature engineering to model training, validation, and deployment.
• Collaborate cross-functionally with engineers, analysts, and product teams to integrate predictive and recommendation models into customer-facing and internal applications.
• Implement scalable ML pipelines using Databricks, PySpark, and Delta Lake, ensuring reproducibility, performance, and maintainability.

measure model performance and quantify business impact.

• Operationalize models through CI/CD and MLOps best practices, including model versioning, monitoring, retraining strategies, and governance.
• Monitor production systems for drift, performance degradation, and anomalies, applying explainability and fairness techniques where needed.
• Contribute to the development of feature stores and reusable data assets to accelerate experimentation and deployment cycles.
• Stay current with emerging trends in ML, MLOps, and cloud data technologies to continuously improve model accuracy, scalability, and efficiency.

What you have…

• Extensive hands-on experience applying machine learning and statistical modelling in production or product-oriented environments.
• Proven understanding of the full spectrum of ML techniques — from traditional models (linear/logistic regression, tree-based methods, ensemble learning) to modern deep learning architectures (CNNs, RNNs, transformers, graph neural networks, diffusion and foundation models).
• Demonstrated ability to design scalable ML pipelines and automate workflows with MLOps tools (MLflow, Kubeflow, Databricks ML runtime, AWS Sagemaker, or AWS Bedrock).
• Preferred experience in Python, with proficiency in Scikit-learn, Autogluone, PyTorch or TensorFlow, and PySpark MLlib.
• Familiarity with retrieval-augmented generation (RAG) and fine-tuning of large language models is a plus.
• Proficiency in SQL and distributed data frameworks, with experience in feature engineering at scale.

Nice to Have

• Familiarity with real-time ML applications, such as online learning, streaming inference, or live recommendations.
• Exposure to forecasting, anomaly detection, or probabilistic modelling in production systems.
• Experience contributing to open-source projects, writing technical blogs, or presenting at data science conferences.
• Interest in continuous learning and keeping up with cutting-edge AI research (e.g., foundation models, self-supervised learning, model compression).