Sai Vamsi Ogety Email : adiov9@r.postjobfree.com
https://osvamsi.github.io/ Mobile : +1-916-***-****
Education
Arizona State University Tempe, AZ
Master of Science in Computer Engineering; GPA: 3.54 Aug. 2018 { May. 2020
PES Institute of Technology Bangalore, India
Bachelor of Engineering in Electronics and Communications; GPA: 4.00 Aug. 2012 { July. 2016 Skills
Programming: Python, SQL, Java, HTML CSS, JavaScript
Libraries: NumPy, Pandas, SciKit-Learn, Keras, Matplotlib, D3.js, OpenCV, Spacy, NLTK.
Cloud and DBMS: GCP, Azure, AWS (EC2 and Sage Maker), MySQL, PostgreSQL
Machine Learning and Deep Learning: Regression techniques, ensemble methods (random forests, gradient and XGBoosting).computer vision techniques (object detection, segmentation and pose estimation) and Sequence Modelling
Frameworks: TensorFlow, PyTorch, Flask, Conda, Django,Docker Experience
Arizona State University Tempe, AZ
Data Scientist Jun. 2020 - Present
Named Entity Recognition: Collaborated with ASU to automate the process of entity extraction, The data-set for training the NLP model is manually labelled using doccano and entities are stored as the meta data which helps in producing relevant search results for document queries.
Article Recommendations: By utilizing the user logs I have built a Rec-System using popularity, collaborative and content based ltering methods. The Hybrid of collaborative and content based methods gave us the best Top-N precision and Recall.
Research Assistant(Machine Learning) Aug 2018 - Sep 2019
Crater Detection: Collaborated with ASU School of Earth and Space Exploration to automate the process of Crater Detection
Building Pipelines: Built an initial baseline model in PyTorch by segmenting images of the lunar surface, manually labeling sub-regions that contained craters, and training a binary classi er to classify each sub-region as either containing or not containing a crater.Built a second modeling pipeline using pre-labeled data, image-segmentation and object detection algorithms like Mask R-CNN and YOLO. The nal model obtained an F1 score of 88.7 for crater detection.
Deployment: Deployed the model as an API endpoint using Flask to make real time detections and published the docker container to Azure Container Registry (ACR).
Wipro Limited Bangalore, India
Project Engineer{Data Analyst Aug 2016 - Jul 2018
Back-end Development: Rewrote our automated query and complaint tracker from Perl into Python/Django to enable greater scalability, speeding up webpage loading by nearly 20%.
Data Analytics: Designed and maintained dynamic reports for key decision-makers. Reports included PL analyses for di erent divisions of Wipro, and on the utilization of our consultants at all client sites, allowing executives to make informed decisions on billing and allocation.Designed and analyzed A/B tests in collaboration with product managers and engineers. Provided data support for product decisions and new feature launches that improved signups by over 12%.
Projects
Video Surveillance as Service : Implemented a video surveillance application to perform object detection on the scale of 100 thousand users. Demonstrated the autoscaling and load balancing functionality implemented from scratch on AWS for thousands of concurrent requests
Spam classi er using Apache Spark : Built an initial pipeline to classify text using Spark MLLib by transforming data into words and then vectors using Feature Hashing. The second pipeline is created on AWS SageMaker to scale this algorithm for larger dataset. The dataset is stored In S3 buckets and later utilized in training on XGBoost algorithm and nally deployed as REST endpoint