Close

Raman Shinde

Machine Learning Engineer

Download Resume

About Me

  • Currently pursuing my career as a Senior Software Engineer with core expertise in Deep Learning, Machine Learning, Python and C++.
  • My work has revolved around architecting ML-driven solutions in products/platforms and getting them live into production.
  • Experience in various ML algorithms(KNN,K-means,Naive Bayes,LR,SVM,DT,Random Forest,GBDT etc.)
  • Experience in building Deep Learning models using components such as LSTM/RNN, CNN, Transformer, Bert, Auto-encoders, Memory Networks, etc.
  • Well versed with platforms such as Docker, Kubernetes. Experience in using GCP/AWS when there’s a need for high computing power.

Experience

Imagination Technologies

Senior Software Engineer [Vision and AI]

  • Working on building SDK to support neural networks to run on Imagination’s GPU and Neural network accelerator.
  • It converts models from all popular frameworks like TensorFlow, PyTorch, Caffe, onnx etc., and creates optimized binaries for custom hardware.
  • Implemented support for LSTM/RNN in NCSDK for Networks present in various frameworks.
  • Developed graph transforms for various operations and operators in RelayIR(TVM).
  • Contributed to the implementation of quantization(static/dynamic quantization, QAT) support for various frameworks.

Xpanxion

Data Scientist

Anthem - Symphony

  • Extracting information from various medical documents with help of AI/ML.
  • IDocument Classification and candidate extraction from classified documents to extract benefits, rates, drug details and plan details.

Digital Access Hub

  • Built various reusable AI/ML components as a part of the Innovation team.
  • Implemented a Recommendation system using content-based/collaborative algorithms.
  • Developed NLP components such as NER, sequence translation, and QnA from the given knowledge base.
  • Worked on Computer Vision use cases like Object localization and detection, Image segmentation and Gesture recognition.

Siemens R&D

Product Development Engineer

  • Developed an application to design and test a manufacturing sequence.
  • Implementation of use cases and bug fixing to support the planned Nx releases.

TCS

Software Developer

  • Developed an application for client NCRA for Monitoring and Controlling antennas.
  • Detecting and debugging the issue reported in an application. Solved the problem of false triggering of alarms with the help of machine learning.
  • Worked in Production Management for client Morgan Stanley.

Education

SGGSIE&T, Nanded

June 2011 - May 2015

B.Tech in Electronics and Telecommunication

Maharashtra State Board of Education

June 2009 - May 2011

Class Xll (HSC)

Maharashtra State Board of Education

June 2008 - March 2009

Class X (SSC)

Deep Learning Projects

Neural Machine Translation using Attention Mechanism

The task is to implement Machine Translator. An attention mechanism was used to deal with longer sequences. After data cleaning and processing, output labels were padded with start and end tokens before feeding to n/w.

Source Code
Demo

Nueral Question Answering(Machine Reading Coprehension)

The objective is to find the correct answer for the given question and context pair. Implemented Standford Attentive Reader. SQUAD v1 dataset was used for this project. Various binary and NLP features were used to get the best results. Compared the final results with fine-tuned BERT model.

Source Code
Demo

Machine Learning Projects

Netflix Movie Recommendation System (Collaborative based recommendation)

The objective was for the given movie and the user to predict the rating given by him/her to the movie. The dataset was obtained from Kaggle. Matrix factorization was used to get similarity matrices. Tried and tested various ML models to get minimum Root Mean Square.

Source Code
Demo

Stack Overflow Tag Prediction

The objective is to predict as many as tags possible with high Precision and Recall. The dataset was obtained from Kaggle. The given problem is a multi-label classification problem. The dataset contains features such as Id, Title, Body and Tags. Data preprocessing and cleaning were done to remove HTML tags and hyperlinks. Micro-Averaged F1-Score was used as a performance metric as mentioned on Kaggle.

Source Code
Demo

Skills

Languages:-

  • Python
  • Node.js
  • C
  • C++
  • JavaScript
  • Data Science
  • Machine Learning
  • Deep Learning
  • AI
  • Data Structures

ML/DL Toolkit:-

  • Keras
  • scikit-learn
  • tensorflow
  • pytorch
  • Onnx

Others:-

  • Docker
  • Kubernetes
  • tensorflow
  • GitHub
  • Perforce
  • Jenkins
  • AWS
  • GCP

Get in Touch