Machine Learning Data Engineer

Name : Karri T

Mobile : +1-945-***-****

Email : *********@*****.***

PROFESSIONAL SUMMARY:

4+ years of experience as a Data Engineer and Machine Learning Engineer, with expertise in building scalable data pipelines and implementing machine learning models to support data-driven decision-making.

Proficient in leveraging Azure Data Factory, Azure Databricks, Azure Synapse Analytics, and Azure SQL Database to design and deploy robust data engineering solutions that enable efficient data processing and storage.

Strong hands-on experience with ETL processes, automating data pipelines, and optimizing data flow for seamless integration across multiple platforms using Azure Blob Storage, Azure Data Lake, and Azure Synapse.

Skilled in machine learning model development, including predictive modeling, classification, and regression, utilizing Azure Machine Learning, Python, scikit-learn, and TensorFlow.

Proficient in transforming raw data into actionable insights using data wrangling, cleaning, and preprocessing techniques, leveraging Pandas and NumPy for efficient data manipulation.

Experience deploying machine learning models in production using Flask, Docker, and Azure Kubernetes Service, ensuring model scalability and integration with existing systems.

Expertise in Natural Language Processing (NLP) and time-series forecasting, applying these techniques to real-world problems such as sentiment analysis and customer behavior prediction.

Strong knowledge of data visualization tools such as Power BI and Tableau, enabling the creation of interactive dashboards to communicate insights and support data-driven decisions.

Hands-on experience with real-time data streaming using Azure Stream Analytics to enable immediate business insights and facilitate timely decision-making.

Familiar with cloud migration, data security, and compliance standards, ensuring smooth transitions from on-premises systems to Azure while maintaining high data integrity and security.

Excellent problem-solving and troubleshooting skills, identifying performance bottlenecks in data pipelines and machine learning models, optimizing them for improved accuracy and efficiency.

Adept in collaborating with cross-functional teams to ensure alignment between business objectives and technical solutions, delivering impactful results.

Actively involved in monitoring and maintaining machine learning model performance post-deployment, ensuring long-term reliability and continuous improvement.

TECHNICAL SKILLS:

Languages: Python, SQL, R, JavaScript

Machine Learning & AI: scikit-learn, TensorFlow, Keras, Natural Language Processing (NLP), LLM (Large Language Models)

Cloud & Data Engineering: Azure (Data Factory, Synapse, Databricks, Azure ML), Azure Blob Storage, Azure Data Lake, PySpark, ETL pipelines

Data Engineering: Data Modeling, SQL, NoSQL, Data Warehousing

Machine Learning: Model Training & Tuning, Predictive Modeling, Time Series Forecasting, Hyperparameter Optimization, Model Deployment (Azure ML)

APIs: REST, Flask, Docker, Azure Kubernetes Service (AKS)

Data Visualization: Power BI, Tableau, Matplotlib, Plotly

CI/CD & Version Control: Git, GitHub, Jenkins, Azure DevOps

Big Data: Apache Kafka, Spark Streaming

Deployment & Orchestration: Docker, Kubernetes, Azure DevOps

PROFESSIONAL EXPERIENCE:

ML Engineer

ICS

Nov, 2024 – Present.

Developed a machine learning model for customer sentiment analysis using diverse feedback sources (surveys, social media, reviews) to generate actionable insights.

Utilized web scraping and API integration to gather large, diverse datasets, ensuring the quality and diversity of data for analysis.

Performed comprehensive data cleaning, including tokenization, stemming, and stop word removal, using Python and Azure tools to prepare the dataset for analysis.

Applied Natural Language Processing (NLP) techniques, transforming raw text data into numerical features using TF-IDF and Word2Vec embeddings to enhance model input quality.

Evaluated various machine learning algorithms (e.g., Naive Bayes, Support Vector Machines, LSTM networks) to determine the optimal model for sentiment classification.

Trained models on labeled datasets, achieving 85%+ accuracy through cross-validation techniques, leveraging Azure Machine Learning for model training and deployment.

Improved model performance through hyperparameter tuning using Grid Search and Random Search, optimizing accuracy and efficiency.

Deployed the final sentiment analysis model using Flask and Docker, creating a RESTful API for real-time sentiment analysis, hosted on Azure Kubernetes Service.

Developed interactive Tableau dashboards and Power BI visualizations to track sentiment trends and provide actionable insights for stakeholders.

Implemented a feedback loop within the model, allowing continuous learning and adaptation based on new data, enhancing prediction accuracy over time.

Integrated Azure Databricks and Azure Data Factory for data ingestion, processing, and transformation, streamlining data flow from various sources to enhance model performance and real-time analysis.

Designed and implemented data pipelines in Azure Data Factory to automate the flow of raw data from various sources to data lakes and analytical platforms.

Leveraged Azure SQL Database for data storage, querying, and analytics, providing robust support for model training and data exploration.

Worked with Azure Synapse Analytics to integrate large datasets, enabling fast data exploration and analysis at scale.

Implemented data versioning and model monitoring in Azure Machine Learning to ensure the model remains up-to-date with changing data and provides accurate predictions.

Used Azure Stream Analytics to process real-time data from various sources, providing immediate insights into customer sentiment for dynamic business decisions.

ML Engineer

Microinfo

Jan, 2024 – Nov, 2024

●Developed a predictive model using Python and scikit-learn to identify potential customer churn with an accuracy exceeding 85%.

●Conducted extensive data exploration and preprocessing, including handling missing values and performing feature engineering to enhance model performance.

●Implemented various machine learning algorithms such as Logistic Regression, Random Forest, and Gradient Boosting, selecting the most effective model for deployment.

●Utilized Azure Machine Learning to streamline the model training and deployment process, ensuring scalability and integration with existing systems.

●Created an interactive dashboard using Power BI to visualize churn predictions and key customer metrics, providing actionable insights for retention strategies.

●Collaborated with cross-functional teams, including data analysts and marketing professionals, to align machine learning outcomes with business objectives.

●Conducted A/B testing on marketing strategies based on churn predictions, measuring the impact on customer retention rates.

●Authored comprehensive documentation detailing the model development process, methodologies, and best practices for future enhancements.

●Monitored and evaluated model performance post-deployment, using metrics to ensure ongoing accuracy and reliability of predictions.

●Presented findings and recommendations to stakeholders, highlighting the impact of predictive analytics on enhancing customer engagement and retention efforts.

Azure Data Engineer.

AARMEC Technology

October 2019 – June 2021

●Built and maintained robust ETL pipelines using Python and Azure Data Factory, ensuring seamless data ingestion, transformation, and loading from various sources.

●Managed and optimized data storage solutions with Azure Blob Storage and Azure Data Lake, improving data retrieval speeds and accessibility for analytics teams.

●Developed efficient data models and schemas in Azure SQL Database and Azure Synapse Analytics, enhancing the performance of complex queries and analytics operations.

●Automated data validation and quality checks using Python scripts, catching data inconsistencies early and maintaining data integrity across systems.

●Implemented Azure Stream Analytics for real-time data processing, enabling instant insights into streaming data sources and facilitating timely business decisions.

●Leveraged Azure Databricks to run large-scale data processing tasks, utilizing PySpark for distributed data analysis and ensuring efficient handling of big data workloads.

●Designed dashboards and visualizations in Power BI to provide stakeholders with actionable insights from processed data, supporting data-driven decision-making.

●Configured and monitored Azure Monitor for tracking data pipeline performance, implementing alert mechanisms to proactively address potential bottlenecks or failures.

●Collaborated with cross-functional teams to understand data requirements and optimize data pipelines for faster and more accurate data delivery.

●Participated in code reviews and documentation of data engineering processes, ensuring best practices and knowledge transfer across the team.

●Worked on data extraction from Azure Cosmos DB and transformed JSON data formats into structured formats suitable for analytics.

●Migrated on-premises data systems to Azure, ensuring data security and compliance with industry standards during the cloud transition.

●Applied Python and Pandas libraries for data wrangling and preprocessing, preparing data for analysis and machine learning model training.

●Integrated Azure Machine Learning for basic data pre-processing and exploratory data analysis, laying the groundwork for upcoming machine learning projects.

●Developed foundational knowledge in ML model deployment and management within Azure environments, setting the stage for future machine learning initiatives.

Contact this candidate