• Led a team in architecting and implementing data engineering and machine learning pipelines, enhancing overall operational efficiency and robustness.• Performed hands-on coding and debugging, specifically targeting data quality issues and implementing advanced noise detection techniques.• Led the implementation of Natural Language Processing (NLP) for efficient data cleanup and developed Large Language Models (LLMs) for precise keyword extraction.• Provided expert mentorship and conducted comprehensive code reviews, while effectively managing the Continuous Development/Continuous Integration (CD/CI) process to streamline software development workflows

Led the team to develop a data quality check system for large scale data quality assurance, anomaly detection, and high-frequency time series data, developing collaborative workflows that generated successful ideas and efficient methods.Created a data-driven drill bit performance tracking system using ML and data analytics approaches by leveraging Python, SQL, Azure Data Factory, Azure ML Pipeline, and Logic Apps to provide accurate information that helped in taking assisted decisions.Developed real-time clustering, reinforcement learning algorithms, and applications on Azure Databricks using Spark, as well as designing ETL processes to incorporate data from on-premise databases to the cloud, performing data quality checks using PySpark.Used Artificial Intelligence and Machine Learning to develop digital products while achieving cost reduction within the estimated time, as well as acting as a program director for the data science certification program, mentoring ~80 domain experts to take the data science initiative. Also, based on my experience and impact on multiple processes and workflows, I presented data science technology showcases to business executives, serving as a committee member to review all data science project proposals at Halliburton.

Developed component-level analytical models with field data, predicting failure risk and integrating to system level for reliability guarantee and cost analysis, as well as developing system-level analytics to equipment health indicators in R that helped in supporting an effective and well-organized maintenance process.Designed and built an integration tool of the reliability model with turbine performance models using VB.net, SQL, and Excel that reduced the cycle time by 60% and used several machine learning algorithms to predict wind turbine velocity profile types based on sensor data. Also, I architected an innovative Predix UI web interface that provided consistent views and interactions across multiple devices and environments for industrial users and not only.Being an experienced and professional member within the industry, I guided to the business on the fast-evolving space of Data Science in areas such as Big Data, Machine Learning, and Predictive Analytics, determining tuning recommendations to improve performance.

Served as an expert consultant that addressed customer problems, traveling to their sites to identify issues and breaches, investigating them, and applying the best solutions to generate expected results.I shared my knowledge by training ~20 application engineers globally on thermodynamic modeling and performance analysis, ensuring that the correct path was chosen to deliver projects within the estimated budget and timeframe.

Performed Root Cause Analysis (RCA) and CFD analyses that were validated with field data and designed thermal and fluid systems for gas turbines based on complex analyzes that helped in identifying solutions for existing issues.Also, I collected and documented modeling requirements, interacting with customers to understand their needs that helped in developing functional design specification and conducting user acceptance tests that validated those business requirements on-time, reducing the risk of defects in production.