Hi, I am Alex Prateek Shankar.
Aspiring ML Engineer
I am currently residing in Bengaluru, India.
A Mathematics Graduate from St. Stephen's College, New Delhi; and a Data Science Post-Graduate from Christ University, Bengaluru.
I enjoy helping people tackle problems using data driven solutions, and love working with a team of individuals striving towards the same goal.
Mail: alex94prateek@gmail.com
Contact: +91 96545 72100
Experience
D.E. Shaw & Co. : Tech Associate (System Administrator)
- Maintained and troubleshot over 30 Windows and Linux based end-user software and applications used within the firm.
- Effectively communicated with colleagues from different Business Units within the firm, to increase understanding of requirements.
- Termination POC: Led the team in handling and regulating the digital cleanup tasks for all of the firm's terminating employees. Assisted in maintaining and updating the code base for all Employee Termination related operations.
- October 2020
- to
- April 2022
Projects
EmoSense:
A Multi-Modal Emotion Detection System
- Developed an accurate system that can detect human emotions through 3 different modalities - Audio, Text and Video.
- Utilized and Fine-tuned SOTA models like Whisper v3, RoBERTa, YOLOv8 and VGG19 and developed a novel SER model.
- Python
- Pytorch
- Deep Learning
- Whisper Large V3
- RoBERTa
- YOLOv8
- VGG19
- Novel model
Neural Style Transfer
- Coordinated the research and development of a Neural Style Transfer project, analyzing recent advances and 2 main techniques.
- Engineered a high-performance NST system with approximately 30% reduction in processing time using L-BFGS optimization.
- Python
- Pytorch
- Deep Learning
- Artistic Image Enhancement
- L-BFGS Optimization
Comparative Analysis of Machine Learning models in Pneumonia Detection
Conducted a comparative analysis on the performance of various machine learning and deep learning models in Pneumonia detection, using Chest X-Rays
- Python
- Logistic Regression
- Support Vector Machine
- Naive Bayes
- K Nearest Neighbors
- Decision Tree
- Random Forest
- CNN
- VGG16
- ResNet
Internships
Open Weaver
- Built 4 Aritifical Intelligence interfaces using the prototype kit called Kandi, applying various AI tools and models.
- Generated over 25 images from audio files, implementing Open AI's Whisper (audio to text) and DALL-E (text to image) tools.
- Designed an interface which takes upto 6 prompts from the user and generates a Story along with a comic strip for the same.
- Python
- Gen -AI
- Machine Learning
- Deep Learning
- May 2023
- to
- June 2023
Skills
Data Science
- Python
- Pandas
- Seaborn
- Sci-kit Learn
- Pytorch
- Jupyter Notebook
- Git
- Power BI
- SQL
Graphic Design
- Adobe Photoshop
- Canva
Music
- Trinity Grade 8 Violinist
- Vocalist
- Guitarist
- Bassist