Devika V Email & Phone Number

United States

United States

Nyc

Responsibilities:•Designed, deployed, and maintained deep learning and ML models using cloud technologies like Vertex AI, Google Storage, GCP Composer, and BigQuery.•Automated data processing and analysis by developing ML pipelines with ML Flow and Apache Airflow, enhancing model building efficiency and accuracy.•Developed CNNs and RNNs for image recognition, NLP, and sequence generation, leveraging advanced Python programming with Scikit-learn and NumPy.•Created a recommendation system using techniques such as content-based and collaborative filtering, ANN deep learning, and LightFM, improving recommendation precision by 60% and click-through rate by 35%. KNN and computer vision models further increased user satisfaction by 25%.•Utilized Spark, SQL, PySpark, Data Lake, TensorFlow, MLLib, and Python for machine learning tasks, including classification, regression, recommendation, and dimensionality reduction.•Wrote complex SQL statements to interact with RDBMS databases for data filtering and analytics.•Developed reports, charts, and visual aids using Power BI and Tableau to support business recommendations.•Researched Large Language Models like GPT and explored Azure Microsoft Copilot Studio for Generative AI applications.•Validated AI models using the K-fold technique to address overfitting and underfitting in deep learning.•Designed the ETL pipelines to automate the ingestion of structured and unstructured data.•Applied clustering techniques such as K-means, Gaussian mixture, and DBSCAN for customer segmentation, product pricing, and customized marketing campaigns.•Engineered Ensemble Models(Bagging, Random Forest, XGBoost, AdaBoost), improving model accuracy by 40%, reducing bias/variance by 30%, and automating processes for a 50% efficiency gain.•Developed MapReduce/Spark Python modules for machine learning and predictive analytics in Hadoop on AWS.

Minnesota

New York City Metropolitan Area

New York, United States

India

India