We provide IT Staff Augmentation Services!

Principal Data Scientist Resume

0/5 (Submit Your Rating)

Trevose, PennsylvaniA

TECHNICAL SKILLS

Machine Learning / Deep Learning: Random Forest, XGBoost, Decision Tree Autoencoder, K - Means, SVM, NLP, OCR, PCA, KNN, CNN, GAN, MLP

Tools: and Frameworks: TensorFlow, Keras, Postgres, MongoDB, Django, Docker, Scala, Python, Kubernetes, REST API Services, SQL, Torch, OpenCV, MySQL, Scikit-Learn, Flask, Kaldi, PySpark, Jenkins, CI/CD Services, NoSQL

Cloud platforms and services: Amazon Web Services (AWS), Microsoft Azure, EC2, RDS, CloudFormation, Lambda, VPC, IAM, Azure Functions, Azure DevOps, S3, DyanmoDB, CloudWatch, LightSail, SageMaker, Cognito, Databricks, Azure Pipelines

PROFESSIONAL EXPERIENCE

Principal Data Scientist

Confidential, Trevose, Pennsylvania

Responsibilities:

  • Led the development of an audio transcription service that processes 200 hours of audio a day
  • Developed a fully automated deployment pipeline for the transcription engine that builds a new docker image, uploads the images to virtual machines via webhooks, and relaunches all of the containers needed to keep up with our continuous stream of audio data
  • Transcription service replaced antiquated 3rd party service which saved us $500,000 a year, gives a higher quality transcription, and is much more customizable to our business needs
  • Created ML models for customer clustering, adviser segmentation, and supply/demand prediction
  • Topic modeling and sentiment analysis on audio and transcribed audio text data gave us valuable insight on our customer activity to provide them with easier access to the services they are looking for
  • Converted our data science team into using a DataBricks environment instead of on-premise servers
  • Grew our data science team completely from start from 1 to 8 individuals.

Founder and CTO

Confidential, Philadelphia, Pennsylvania

Responsibilities:

  • Networked with clients to find their companies’ data needs and provide them with custom made solutions
  • Image processing web application that could ingest an image, process it with various filters, and output the resulting image all through a single API request.
  • The main function was a model that could detect cracks in infrastructure that was taken from drone footage
  • Built a Deep learning model in the health care industry for one large pharmaceutical company to replace in-house statisticians’ model of active ingredient detection in drugs using Raman Spectroscopy data. We beat their team’s accuracy by a significant amount using a very small amount of data.
  • Created an advanced search tool to read through medical papers to automatically find side effects of specific drugs
  • Text payment platform where users can submit a payment by sending a text message from their own device
  • Custom solution for stock market analytics for a trading firm
  • Set up, hosted, and monitored websites and APIs in an AWS environment

Data Engineer / Full-Stack Developer

Confidential, Philadelphia, Pennsylvania

Responsibilities:

  • Create and run large SQL reports on our vaccine, STD, and public health big data Monitor the flowing of data into our data lake Set up connections with hospitals, clinics, and doctor’s offices to allow their data to flow into our data lake Maintain our main web application for our researchers to view and access our data

We'd love your feedback!