Pooja Choudhary

I build and run production-grade data and machine learning systems.
My work focuses on reliable data pipelines, real-time processing, and deploying ML models into day-to-day business use.

I have 8 years of experience working with data-intensive systems across finance, healthcare, and automotive, where I’ve owned pipelines from ingestion to inference. This includes batch and streaming workloads, model deployment, monitoring, and operational stability.

What I work on in practice:

- Designing and maintaining scalable data pipelines (Python, PySpark, SQL)
-Real-time and near–real-time processing using Kafka and Spark
-Deploying and operating ML models with MLflow and model serving
-Building systems that teams can monitor, debug, and extend

Core stack (hands-on):

-Databricks (Delta Lake, MLflow, Feature Store, Model Serving)
-Azure data platform (ADF, Data Lake, Synapse, Azure ML)
-Airflow, Kafka, Spark Structured Streaming, Git, CI/CD

Recent work includes:

-Production lead-scoring model used by business teams
-ML pipelines to optimize marketing spend and customer targeting
-Customer segmentation and personalization systems
-NLP chatbot integrated with Salesforce workflows

I work at the intersection of data engineering and ML engineering, with a strong bias toward production, stability, and measurable outcomes.

I build and run production-grade data and machine learning systems.
My work focuses on reliable data pipelines, real-time processing, and deploying ML models into day-to-day business use.

I have 8 years of experience working with data-intensive systems across finance, healthcare, and automotive, where I’ve owned pipelines from ingestion to inference. This includes batch and streaming workloads, model deployment, monitoring, and operational stability.

What I work on in practice:

- Designing and maintaining scalable data pipelines (Python, PySpark, SQL)
-Real-time and near–real-time processing using Kafka and Spark
-Deploying and operating ML models with MLflow and model serving
-Building systems that teams can monitor, debug, and extend

Core stack (hands-on):

-Databricks (Delta Lake, MLflow, Feature Store, Model Serving)
-Azure data platform (ADF, Data Lake, Synapse, Azure ML)
-Airflow, Kafka, Spark Structured Streaming, Git, CI/CD

Recent work includes:

-Production lead-scoring model used by business teams
-ML pipelines to optimize marketing spend and customer targeting
-Customer segmentation and personalization systems
-NLP chatbot integrated with Salesforce workflows

I work at the intersection of data engineering and ML engineering, with a strong bias toward production, stability, and measurable outcomes.

Bachelors in Computer Science and Engineering