Kuldeep is a Graduate Research Assistant at IIT Hyderabad (Dept of CSE) under Dr. Ramakrishna Upadrasta currently working at the intersection of Deep Learning and Compilers for code comprehension and code optimization. He has a demonstrated history of working in ML/DL Stack and has industry experience of working as a Software Engineer at Samsung Research Institute, Noida, and as a Data Science Intern at SIPI-IP, Noida. He has also worked on several academic projects in the same domain during his undergraduate years.

SKILLS: C, C++, Python, Machine Learning, Deep Learning, Computer Vision, Natural Language Processing.

Academic Projects


Collection of ML algorithms implemented from scratch.

Logistic Regression Numpy based implementation of logistic regression with log loss as the loss function. It includes utility for fit, predict and score functions, similar to scikit-learn API.
Decision Trees Implementation of entropy and gini-index based decision tree classifier. It also includes implementation of K-Fold cross validation from scratch.
Random Forests Implementation for entropy and gini-index based random forest classifier, making use of the decision tree module built in the above project. It also provides utility functions for fitting, predictions, out of the bag score and performs at par with scikit-learn RFC API in accuracy. Sensitivity to max_features parameter and OOB error has also been explored.
Feed Forward Neural Networks Tensorflow based implementation of FF-NN. Adam optimizer has been used to perform the backward pass only using TF API. Results in an accuracy of 96.6% on MNIST dataset.
Density-Based Spatial Clustering of Applications with Noise (DBSCAN) Implementation of DBSCAN method of clustering. Used euclidean distance for getting points in epsilon neighborhood and separates the points into core, border and noise points. Only core points and border points are used to define boundary lines for clusters. Performs at par with scikit learn implementaton.


Collection of basic Deep Learning projects.

DNN based Face Detection ResNet10 architecture based face detection project implemented using OpenCV and Caffe implementation of ResNet10 architecture (pretrained).
Automated Essay Scorer Word2Vec based essay scoring project using LSTMs to process the word vectors in the sentence.
Pipeline includes: removal of stopwords, punctuations, special characters, lowering of cases, removing numeric values, stripping spaces, and tokenization. K-Fold CV for determining the results on validation dataset and ensuring performance on test dataset. The results are then evaluated for Mean Squared Error, Variance and Cohen’s Kappa Score.


Collection of classification/regression challenges on Kaggle.

The Titanic competition (Accuracy: 78.4%)
Driver Fault competition (Accuracy: 84.38%)
The Housing competition
Taxi Fare competition

Pipeline includes:
• Preprocessing of data.
• Dealing with missing values using impuation methods like mean, median, etc.
• Coversion of categorical values using label encoder followed by conversion to one-hot vector for training.
• Feature engineering for merging features and creating new features like age bands, days of the week, month of the year, etc.
• Feature selection methods like forward feature selection, backward feature elimination and PCA for dimensionality reduction.
• Model Building, Hyperparameter-Tuning using grid search and Evaluation using evaluation metrics such as confusion matrices, accuracy, etc.

Method Name Preprocessor

• Implemented a text preprocessor using trie data structure to preprocesses short method names to meaningful method names as given in English dictionary alongwith a custom dictionary containing CS related words/acronyms.


Graduate Research Asst.

IIT, Hyderabad

• Working as a Research Asst. under Dr. Ramakrishna Upadrasta at Scalable Compilers for Heterogeneous Architectures Group, IIT Hyderabad.
• Actively carrying out research based on Machine Learning in Compilers and Programming Languages.
• Paper presentations and creating surveys of research papers for state-of-the-art works to understand the approach and reproducing & evaluating the results.
• Mentoring juniors in the research group.
• Teaching Assistant for Compilers-1, Compilers-2, and Compiler Optimizations.
• Responsible for maintenance and updates of the team website.
• Organised ACM India Summer School, 2021 on Programming Language Analysis and Optimizations, hosted by IIT Hyderabad, in collaboration with ACM India Council and NVIDIA.

Software Engineer

Samsung Research Institute, Noida

• Maintaining code quality & compatibility.
• Developing ML models for sentiment analysis and a tool automation.
• Delivering team trainings.
• Project Management.

Data Science & NLP Intern

Digital IP Insights Pvt Ltd, Noida

• Implemented a computer vision model for image comparison.
• Implemented a python script for translating large data in foreign languages to English for better text processing.
• Developed a chrome extension for a marketplace for scraping the data.



Dept. of CSE

IIT, Hyderabad

2020 - 2022


Dept. of CSE

AKGEC, Ghaziabad

2015 - 2019



DPS, Mathura


High School

Grace Convent School, Mathura