Summary
Overview
Work History
Education
Skills
Timeline
Vamsi Nimmala

Vamsi Nimmala

Collierville,Tennessee

Summary

I love to build computational tools that solve complex open-ended problems. In the past work I have implemented various ML use cases with business acumen, Overall 7+ years of experience in the data centric field. I have created machine learning tools for use in a variety of domains and also excited about using these technical skills in areas that have a big impact on people's everyday lives.

Overview

9
9
years of professional experience

Work History

Sr Machine Learning Engineer

AT&T
Dallas, Texas
11.2020 - Current
  • Recognize patterns of fraud and suggest new methods of detection, mitigation, and prevention.
  • Worked on Azure Databricks ecosystem to create tables, cluster, and workbooks to create programs geared towards specific use cases and creating workflows to encompass all requirements.
  • Worked with different formats of data like JSON, AVRO, delta to different types of data ranging from histograms, streams, granular data to collect and then transform it using data wrangling tools like Python, Spark to use cases and deliver insights.
  • Responsible for processing, cleansing, and verifying integrity of data used for analysis and focus on developing solutions for identifying patterns or trends

Sr NLP Developer

Social Security Adminstration
Catonsville, MD
03.2018 - 10.2020
  • Supported Natural Language Processing (NLP) pipeline which extracts clinical concepts, metadata about these concepts such as assertions of conditionality or negation and document level characteristics like encounter type from unstructured data sources like images of medical documents which allows end users to explore, search and filter case documentation in customized intelligent viewer.
  • Successfully built python web services using frameworks like Flask, Bottle, Gunicorn to integrate and productize best performing hierarchical XG Boost and Tensor-flow models.
  • Applied feature engineering techniques like TF-IDF, TF-PDF, Jaccard similarity, Word2VEC, N-Grams, Cosine similarity, Skip-grams., etc. on training data and created numeric vectors for training the models.
  • Utilized open-source tools like TensorflowOnSpark, Sparkflow to integrate Tensorflow on apache spark cluster for advantage of implementing distributed training with neural net models to effectively using spark cluster available.
  • Approached classification problems using boosting techniques for different use cases which meets business requirements and evaluated these models along with SME to reduce false positives or false negatives as per use cases which is important for the business.
  • After POC approvals, created automated pipelines for training both XG Boost models and Neural Net models which performs reading big data, applying filters on data as per use case, transform data, training, save all intermediate file for QA, save the models for evaluation.

Data Scientist, Junior

Los Angeles Department Of Health Services - HMT
Hyderabad, Andhra Pradesh
12.2013 - 05.2015
  • Built RESTful APIs which not only uses the mathematical models trained on historical data for predictions but also filtering by optimal cutoff functionality which cannot always be derived solely mathematically but requires collaboration with SMEs, an understanding the purpose of the classifier and the underlying quality of the labels that are being used for modeling.
  • Collaborated with senior data scientists to analyze and perform ad-hoc analysis, AVONA, Hypothesis test on the data to identify patterns on the dataset and to apply both ML/DL techniques

Software Developer

Hallmark Global Technologies
Hyderabad, Andhra Pradesh
02.2013 - 12.2013
  • Consolidated and refactored legacy program modules which significantly improved the performance and decreased deployment time by 50%.
  • Developed new API with design support of senior developers and created unit test cases for different scenarios.
  • Performed POC's on NoSQL databases. Implemented NoSQL databases like Mongo in Dev/Test environment.

Education

Master of Science - Computer And Information Sciences

Midwestern State University
05.2017

Skills

  • Source and Version Control: Git, GitHub, Bitbucket
  • API Design and Development
  • Programming Languages: Python, R, Javascript
  • Performance Evaluation and Optimization

Timeline

Sr Machine Learning Engineer - AT&T
11.2020 - Current
Sr NLP Developer - Social Security Adminstration
03.2018 - 10.2020
Data Scientist, Junior - Los Angeles Department Of Health Services - HMT
12.2013 - 05.2015
Software Developer - Hallmark Global Technologies
02.2013 - 12.2013
Midwestern State University - Master of Science, Computer And Information Sciences

Similar Profiles

CREATE PROFILE
Vamsi Nimmala