Senior Data Engineer with Cloud & ML Experience

+1-716-***-**** ***********@*****.*** https://github.PUJA com/KUMARI pujakumaribuffalo https://www.linkedin.com/in/pujakuma1995/ PROFESSIONAL SUMMARY

TECHNICAL Results-expertise actionable driven in insights Python, SKILLS Data and Engineer SQL, collaborating Apache with Spark, 8+ across years GCP of teams and experience AWS to drive to design building data-and driven scalable optimize business data data pipelines, outcomes. workflows ETL supporting processes, ML and and analytical analytics. systems Adept in at cloud transforming environments. raw data Proven into

• • • • • • • • Certifications Programming: Big Databases Cloud Machine Visualization: Frameworks: Tools: Data Platforms: & Learning: & ETL: Warehousing: Python, Apache MySQL, AWS XGBoost, Power TensorFlow, Git, Data Docker, Engineering, (EC2, BI, Spark, Redis, SQL, Random Tableau, S3, Kubernetes, PyTorch, C, Amazon Lambda, Hadoop, Swift SQL, Forest, Excel, NumPy, Machine Redshift, Apache RDS)Jenkins Matplotlib, Logistic, GCP Pandas, Airflow, Learning, Google Agile/Regression, Seaborn Scikit-Apache SCRUM BigQuery Power learn SVM, NiFi, BI, K-Tableau, Kafka Means, Pandas, Ensemble Python, Methods Lean Six Sigma, Big Data, GCP WORK Senior Engineer, EXPERIENCE Data Science Hughes Network System May 2025 - Present Project: Cause Analysis • • • • Arcana: Built API Secured tables. Flattened Stored (RCA) and A and comprehensive processed SNMP pipelines the deployed and pipeline enriched to collect data an with automated Retrieval-in collected VPN, Google Google VDOM, Augmented Cloud data Secret NOC and with Data Storage Manager network BigQuery Collector Generation (GCS) for statistics. API lookups and & Aggregator (RAG) credentials BigQuery for system SAN/pipeline for and CLID specifically historical developed mapping. on GKE trend designed that logging analysis runs for & every monitoring managed and 10 troubleshooting. minutes, telecom to track integrating service health and providers with errors FortiGate to in support BigQuery firewalls automated app via status REST Root Data Engineer (Cloud and ML) Eitacies Inc. Jul 2024 – Apr 2025 Project: Cyber Threat Detection

Data Engineer • • • Spearheaded Enhanced and Developed the testing Apache TALENTICA foundational and and Spark cybersecurity engineering deployed SOFTWARE to ingest, a ML CI/initiatives teams. models clean CD pipeline and with leveraging transform domain-in a Docker Azure specific (data environment and pre-data, Google processing)heightening Vertex to automate . AI/cyber ML the services, threat build, protection. fortifying test, and commit threat Built a detection processes, scalable and data streamlining automatic pipeline Oct remediation. using the 2019 workflow Python - Jan 2023 for Project: CAMERA EATS FIRST - An app to recommend the best meals in your vicinity, discover new food, and put the spotlight on your favorite eats. Project: • • • Real-Designed Designed Library) Developed time from inventory an and and ETL implemented SparkML deployed pipeline forecasting to the accurately using a application spotlight PySpark for an predict feature ad using to mediation streamline optimal AWS using services Apache food platform. data options clow Spark, such to based as leveraging ML API models, on Gateway, locality the resulting ALS and Cognito, (Alternating user in a preferences. 30% EC2, Lambda, reduction Least Squares) RDS, in data and algorithm processing S3. (Recommender time. System SOFTWARE • • • Developed Kabka, Implemented forecasting Excelled global ENGINEER locations. Apache in data Agile accuracy various TALENTICA Spark, processing environment, bine-by Python] 12%SOFTWARE tuned pipeline .translating [Python, machine for many XGBoost, business learning different Random needs models sets into Forest, of (data XGBoost, actionable SparkML] (Historical Decision solutions, Data, Trees, Real managing Random time Data, weekly Forests) publisher sprints, to forecast Data, facilitating Trafcic inventory communication patterns, which Oct etc) 2017 increased [Apache across - Sep the 4 2019 Project: Project: SOFTWARE • • • • • • • AUTODESK WORLDMAP Improved Led Designed Honored Developed Used Honored ENGINEER a PubNub team and with with the BIM360 iOS of SHARING at implemented app 5 library and a the members NINELEAPS pat performance HoloLens Vulcan - on A for - construction A the data virtual and Inc. a back Technology apps, CI/sharing served Ideas by CD map award 11% facilitating pipeline app to that across as by to Innovation twice SPOC can plan, optimizing with all be shared by three for model, accessed Jenkins Talentica the Award platforms. memory augmented & client for execute as for automated for a for shared usage “Supporting drastically quality any reality & experience technical business deployment. & safety improving experiences. the or logic. vision between workflows functional the of app iOS, Paul on performance. Android, concerns. the G. Allen”. phone. and Founded HoloLens by users. Jody & Paul Jun 2016 G. Allen - Sep 2017 Project: Project: EDUCATION • • • • FLUID OLIVIA Implemented Managed Leveraged Researched - - A AI-credit this powered REST on app’s custom app battery APIs that data finance animations, to optimization helps enhance using app. 2 Core million Received user integrated Data and experience US run-& special students Realm with time by mention REST optimization Database. build providing APIs credit on & the personalized for third-by AppleTV borrowing the party app. show: libraries. insights money. Planet based of on the user Apps. behavior and preferences. Bachelor University Master Visvesvaraya of of Science Technology at Buffalo National – Data (SUNY Institute Science Buffalo)of Technology, NY (VNIT), Nagpur May Jan 2023 2012 - - June May 2016 2024