Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm a Data Scientist with around five years of experience delivering end-to-end solutions across financial services. I specialize in Python, R, and SQL, and I work with big data ecosystems like Hadoop, Spark, Kafka, and Hive to build fraud detection, forecasting, and sentiment analysis models. I’m hands-on with ML and deep learning (TensorFlow, PyTorch, GANs, LSTMs), NLP (Transformers, LangChain), and MLOps (Kubeflow, MLflow, Airflow, Docker, Kubernetes). I also design scalable cloud-based deployments on AWS, GCP, and Azure, optimize data pipelines for cost efficiency, and communicate insights to stakeholders.…I'm a Data Scientist with around five years of experience delivering end-to-end solutions across financial services. I specialize in Python, R, and SQL, and I work with big data ecosystems like Hadoop, Spark, Kafka, and Hive to build fraud detection, forecasting, and sentiment analysis models. I’m hands-on with ML and deep learning (TensorFlow, PyTorch, GANs, LSTMs), NLP (Transformers, LangChain), and MLOps (Kubeflow, MLflow, Airflow, Docker, Kubernetes). I also design scalable cloud-based deployments on AWS, GCP, and Azure, optimize data pipelines for cost efficiency, and communicate insights to stakeholders.

Pavan Sai Dasari

Data Scientist, AI Engineer, AI Developer, +2





I'm a Data Scientist with around five years of experience delivering end-to-end solutions across financial services. I specialize in Python, R, and SQL, and I work with big data ecosystems like Hadoop, Spark, Kafka, and Hive to build fraud detection, forecasting, and sentiment analysis models. I’m hands-on with ML and deep learning (TensorFlow, PyTorch, GANs, LSTMs), NLP (Transformers, LangChain), and MLOps (Kubeflow, MLflow, Airflow, Docker, Kubernetes). I also design scalable cloud-based deployments on AWS, GCP, and Azure, optimize data pipelines for cost efficiency, and communicate insights to stakeholders.…I'm a Data Scientist with around five years of experience delivering end-to-end solutions across financial services. I specialize in Python, R, and SQL, and I work with big data ecosystems like Hadoop, Spark, Kafka, and Hive to build fraud detection, forecasting, and sentiment analysis models. I’m hands-on with ML and deep learning (TensorFlow, PyTorch, GANs, LSTMs), NLP (Transformers, LangChain), and MLOps (Kubeflow, MLflow, Airflow, Docker, Kubernetes). I also design scalable cloud-based deployments on AWS, GCP, and Azure, optimize data pipelines for cost efficiency, and communicate insights to stakeholders.

Available to hire

I’m a Data Scientist with around five years of experience delivering end-to-end solutions across financial services. I specialize in Python, R, and SQL, and I work with big data ecosystems like Hadoop, Spark, Kafka, and Hive to build fraud detection, forecasting, and sentiment analysis models.

I’m hands-on with ML and deep learning (TensorFlow, PyTorch, GANs, LSTMs), NLP (Transformers, LangChain), and MLOps (Kubeflow, MLflow, Airflow, Docker, Kubernetes). I also design scalable cloud-based deployments on AWS, GCP, and Azure, optimize data pipelines for cost efficiency, and communicate insights to stakeholders.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Advanced

Work Experience

Data Scientist at Capital One

January 1, 2024 - November 6, 2025

Applied Python, R, and SQL on multi-terabyte Hadoop and Spark clusters to address inconsistent data pipelines and streamline ETL workflows; refined forecasting models with XGBoost and LSTMs to reduce credit risk misclassification and false approvals; implemented Kubeflow pipelines for retraining models on AWS SageMaker; improved sentiment detection using NLP with Transformers and LangChain; automated data quality checks with dbt and Airflow; used GANs for synthetic data augmentation to boost recall; deployed real-time streaming for anomaly detection with Kafka and Kinesis.

Data Scientist at Borland Software

July 1, 2022 - July 1, 2022

Optimized SQL Server and Snowflake queries, reduced average query runtime by 65% and cut cloud compute costs; integrated explainable AI into credit models for regulatory compliance; deployed Docker and Kubernetes to host models; built interactive Tableau dashboards with Redshift feeds; conducted A/B testing for marketing strategies; migrated MATLAB models to TensorFlow/Keras; built vector DB pipelines with Pinecone + AWS; enhanced monitoring with Prometheus, Grafana, and ELK to reduce outages.