Data Engineer Real-Time

Eeshan Mundhe

Data Engineer

+1-551-***-**** New York City, NY

************@*****.*** LinkedIn GitHub Google Scholar Professional Summary

Data Engineer specializing in Java, Python, SQL, and C++ for building scalable and high-performance data infrastructure. Expertise in designing and maintaining robust ETL pipelines, optimizing data workflows, and ensuring data quality across distributed systems. Skilled in database management, automation scripting, and integrating third-party data sources through APIs. Proficient in data visualization tools like Tableau, Power BI, and Excel. Published researcher with multiple contributions to international scientific conferences. Work Experience

Data Engineer Aug 2024 - Present

Thera VR Inc. New York City

Developed AI-driven predictive models for healthcare trend analysis using Python, SQL, and Apache Spark, optimizing real- time insights and data processing.

Designed and implemented deep learning models for facial and behavioral recognition in virtual environments, utilizing Python and improving detection accuracy.

Achieved 89% accuracy in object detection for VR-based applications with YOLOv8, leveraging Kafka for real-time data streaming and enhancing interactions.

Built and deployed custom object detection and classification models in Python to support immersive healthcare simulations, contributing to advancements in virtual healthcare analytics.

Designed, trained, and deployed machine learning models on Google Cloud Vertex AI, integrating with Apache Spark and Kafka for seamless predictive analytics and real-time data streaming.

Developed a behavioral analysis model using YOLOv5 and mAP50, leveraging Apache Kafka to stream real-time data and enhance user engagement in metaverse healthcare platforms. Consultant Data Engineer Sep 2022 - May 2024

Courant Institute of Mathematical Sciences, NYU New York City

Developed and deployed scalable RESTful APIs for real-time video processing and metaverse applications using on Azure VMs.

Designed secure, high-performance APIs for healthcare data exchange, tested thoroughly with JUnit to ensure system reliability.

Automated deployment of API services and data workflows using Argo on Kubernetes, with backend services in Scala for scalability.

Transformed raw video and sensor data into structured formats using Python for preprocessing, enabling smooth integration with Java-based APIs.

Quantitative Analysis Summer Analyst Jun 2023 - Aug 2023 Citi New York City

Conducted technical analysis of prepayment schedules, default rates, and LTV ratios for mortgage tranches, and developed time series forecasting models to enhance trading strategies using Python.

Improved the accuracy of stochastic and statistical models for predicting PD and LGD, supporting quantitative risk assessments of MBS, with model deployment and integration handled in Java.

Enhanced data matching algorithms (e.g., fuzzy string matching) and streamlined preprocessing of equities market data using big data tools and Python, ensuring model training consistency and quality.

Integrated high-performance C++ analytics libraries into Java-based trading systems using Java Native Interface (JNI), enabling low-latency execution of quantitative models within real-time trading workflows. Data Engineer Aug 2021 - Aug 2022

Barclays Pune, India

Developed and maintained backend components for a Sales & Trading platform’s payment data settlement feed using Java and C++, with real-time data ingestion via Apache Kafka.

Optimized distributed computing workflows and reduced query latency using Apache Spark, enhancing the performance of trading systems accessed by multiple trading teams.

Built and tested RESTful APIs for data processing and integration, automated data validation workflows for ETL using SQL Server Integration Services, and implemented BDD test scenarios with Cucumber. Software Engineer June 2019 - Jun 2021

Software Development Cell at K J Somaiya College of Engineering Mumbai, India

Contributed to the analysis, design, and development of an Attendance Management Portal and a Virtual Lab Experiment using Java/J2EE, Spring MVC, Struts 2.0, Hibernate, Servlets, and SQL Server, deployed on IBM WebSphere and JBoss.2.

Developed responsive front-end features using JSP, HTML, CSS, Angular, and NodeJS, with session validation through Spring AOP and automated attendance reporting using Java multithreading and batch jobs.

Ensured high availability through Oracle clustering on WebLogic Server 10.3, improved system reliability with Linux shell-based health monitoring, and streamlined communication via an HTML/CSS newsletter module. Core Skills

Programming Languages and Big Data Technologies: Java, Python, C++, Scala, Golang, SQL, KDB+/Q, R.

Tools, Libraries and Frameworks: PyTorch, TensorFlow, Numpy, scikit-learn, spaCy, Flask, Angular 8, SQLite, Singularity, Pandas, Statsmodels. Scala, Spark, Kafka, Hadoop. SAS, MATLAB, Tableau, Power BI, AWS, Azure ML Studio, GCP (AI). Jenkins, Git, Docker, Kubernetes, MongoDB, SQL Server Integration Services. Scientific Research Publications

A Novel Encryption Algorithm Using Random Number Generation for Ciphertext Expansion Springer Nature

Live Cricket Prediction Web Application Using Machine Learning IEEE

Web Application for Machine Learning based Music Genre Classification IEEE

A Contactless IoT Based Intelligent Parking Solution for Smart Cities International Journal of Computer Applications Projects

Tic Tac Toe Golang

Using Test Driven Development (TDD) and Objected Oriented Design, developed a game of Tic Tac Toe in Golang.

Twitter Bot for Sentiment Analysis of Sports Matches Java Analyzed live hashtags using Twitter4j API, to evaluate sentiment for teams/players for regional insights into the game.

Revenue Prediction System for Hospital Python

Implemented Time Series Analysis to predict revenues using ARIMA model for various diagnostic departments in the hospital. Education

NYU Courant Institute of Mathematical Sciences and Stern School of Business Sep 2022 - May 2024 Master of Science in Computer and Information Science Coursework: Fundamental Algorithms, Robo Advisors and Systematic Trading, Foundations of Finance, Data Science for Business, Data Analytics and Visualization for Healthcare, Cryptocurrencies and Decentralized Ledgers, Firms and Markets, Global Economy. University of Mumbai Aug 2017 - Jun 2021

Bachelor of Technology in Information Technology

Coursework: Data Structures, Operating Systems, Computer Architecture, Object Oriented Programming, Advanced Databases, AI & ML, Applied Mathematics, Numerical Techniques, Big Data Analytics, Cloud Computing, Computational Biology & Bioinformatics. Achievements – Technical head of Math Club in Undergrad; 5 stars on Hackerrank for Java and Problem Solving with Math; Ranked among top coders at HackWithInfy 2020; Rank 1 in Undergrad University Coding Competition “Codeinja” (2020). Ramanujan Scholarship in Junior Math Olympiad India (2012); All India Rank 18 in National Mathematics Talent Search Competition (2009).

Contact this candidate