Machine Learning Engineer with 5+ years of experience with a proven track record of successfully delivering impactful projects across various domains. Over the course of my career, I have led and contributed to projects that showcase my expertise in designing and implementing advanced machine learning solutions. One of my notable achievements includes spearheading the development of a Text Summarization System using cutting-edge Large Language Models (LLMs) and LangChain. This project not only demonstrated my proficiency in natural language processing but also showcased my ability to translate complex concepts into practical and effective solutions. As a MLE developed end to end pipelines with proper CI/CD. In another endeavor, I played a pivotal role in the creation of a custom rules-based Model Selection Engine for competing models. This engine, marked by its configurability, has significantly enhanced decision-making processes in model selection, showcasing my dedication to creating tailored solutions for unique challenges. As a project lead, I orchestrated the end-to-end deployment and integration of machine learning models in production environments, ensuring seamless execution and real-world impact. My experience extends to building robust machine learning pipelines in PySpark, incorporating algorithms such as Prophet and SARIMAX for accurate and meaningful sales predictions over several years. Additionally, I have a strong background in data preprocessing and transformation, utilizing various ML transformers and estimators to handle extensive datasets. My expertise further extends to ETL pipeline migrations, with a successful track record of migrating pipelines from Azure Data Factory and Databricks to Astronomer/Airflow and Google Cloud Platform, handling data extraction, transformation, and loading on a massive scale. I have also led the development of a model automating the classification of tax entries, streamlining the reversal of accrued tax journal entries and eliminating unnecessary financial burdens. Furthermore, I've successfully implemented real-time prediction pipelines using FAST API, retraining models on a weekly basis to ensure accurate and up-to-date predictions. Skills: Languages: Python, Pyspark, C#, Scala, C++ Python: Pandas, Numpy, Tensorflow, Sci-kit learn, Plotly, Matplotlib Apache Spark, Hive, Airflow, Astronomer GCP: Google Dataproc, Google Big Query, Google Coud Storage Azure: Azure Data Factory, Blob Storage, Databricks Business Intelligence: MySQL, SQL, Elastics Search, MS SQL, DBeaver and Microsoft Excel Competencies: Data Analysis, Statistical Modeling, Machine Learning, Deep Learning, AB testing, Data Visualization, Feature Engineering, Data Wrangling, Data Governance, CI/CD Leadership, GIT, Docker, Jenkins & Linux…Machine Learning Engineer with 5+ years of experience with a proven track record of successfully delivering impactful projects across various domains. Over the course of my career, I have led and contributed to projects that showcase my expertise in designing and implementing advanced machine learning solutions. One of my notable achievements includes spearheading the development of a Text Summarization System using cutting-edge Large Language Models (LLMs) and LangChain. This project not only demonstrated my proficiency in natural language processing but also showcased my ability to translate complex concepts into practical and effective solutions. As a MLE developed end to end pipelines with proper CI/CD. In another endeavor, I played a pivotal role in the creation of a custom rules-based Model Selection Engine for competing models. This engine, marked by its configurability, has significantly enhanced decision-making processes in model selection, showcasing my dedication to creating tailored solutions for unique challenges. As a project lead, I orchestrated the end-to-end deployment and integration of machine learning models in production environments, ensuring seamless execution and real-world impact. My experience extends to building robust machine learning pipelines in PySpark, incorporating algorithms such as Prophet and SARIMAX for accurate and meaningful sales predictions over several years. Additionally, I have a strong background in data preprocessing and transformation, utilizing various ML transformers and estimators to handle extensive datasets. My expertise further extends to ETL pipeline migrations, with a successful track record of migrating pipelines from Azure Data Factory and Databricks to Astronomer/Airflow and Google Cloud Platform, handling data extraction, transformation, and loading on a massive scale. I have also led the development of a model automating the classification of tax entries, streamlining the reversal of accrued tax journal entries and eliminating unnecessary financial burdens. Furthermore, I've successfully implemented real-time prediction pipelines using FAST API, retraining models on a weekly basis to ensure accurate and up-to-date predictions. Skills: Languages: Python, Pyspark, C#, Scala, C++ Python: Pandas, Numpy, Tensorflow, Sci-kit learn, Plotly, Matplotlib Apache Spark, Hive, Airflow, Astronomer GCP: Google Dataproc, Google Big Query, Google Coud Storage Azure: Azure Data Factory, Blob Storage, Databricks Business Intelligence: MySQL, SQL, Elastics Search, MS SQL, DBeaver and Microsoft Excel Competencies: Data Analysis, Statistical Modeling, Machine Learning, Deep Learning, AB testing, Data Visualization, Feature Engineering, Data Wrangling, Data Governance, CI/CD Leadership, GIT, Docker, Jenkins & LinuxWWWW…