Lead Machine Learning Engineer2018 - PRESENTBraided Data Solutions Inc
Technologies: Tensorflow, PyTorch, Kubernetes, Django, Celery, Stanford-corenlp, Tesseract, OCR, C++, Python
- Built a document processing system from ground up to make a PDF document searchable with OCR and perform redaction in real-time. Implemented OCR system capable to process millions of pages and already processed several billion words.
- Trained several state of the art in text processing GPT-2 and BeRT model to perform high accuracy tag recognization. Invented patentable realtime NER algorithm to process and learn without catastrophic interference.
- Customised the source code of largest OCR tool in the market Tesseract to allow table recognition. Built a Kubernetes cluster to perform on demand autoscaling and processing.
- Lead team between multiple projects in the company and coordinated with multiple projects. Coordinated in multiple time zone.
Chief Scientist and Software Engineer2015 - PRESENTF(x) Data Labs PVT LTD
Technologies: TensorFlow, Python, Keras, Machine Learning, Neural Networks, Data Structures, C/C++, PHP, Laravel 5, AngularJS, Angular 4, Bootstrap 3/4, MySQL, Go
- Invented the fastest data retrieval algorithm h+Tree that had an up to 300% speed increase than the conventional b+tree—this was particularly useful for all the popular databases like MySQL, PostgreSQL, MongoDB, SQLite, etc. The system was translated into several languages including C/C++, Python, and Scala.
- Created a full-stack public cloud on the latest version of OpenStack with an infrastructure as a service, database as a service, and object storage service. The system was built with OpenStack, Python, Ansible Notebooks, Ubuntu 16.04, and Python unit tests.
- Developed an artificial intelligence based enterprise resource planning (ERP) system for a 60-year-old real estate company with help of TensorFlow, a deep neural network, Laravel, Angular 4, Frappe, Python, MySQL, Ubuntu 16.0, and unit tests.
- Built a loan prediction default system with an accuracy of 99.4% with help of TensorFlow, Python, and R. It also predicted the loan default amount with a 96.3% accuracy.
- Implemented baby-cry detection with sound classification along with support vector machines (SVM) on Raspberry Pi to notify parents when a baby is crying.
- Developed video classification with a deep neural network to detect different human gestures from the video as small clips; used an artificial neural network, Caffe 2.0, C/C++, convolutional neural network, and Nvidia CUDA.
- Created a hospital-operation-room scheduler with artificial neural networks, Python, Laravel, Angular 4, CSS3, Vagrant, and unit tests.
- Enabled video style transfers for 3D videos for an artificial neural network with PyTorch, Google Cloud, CUDA, and more.
- Created 3D face mesh model from a single mobile camera based selfie with an accuracy of more than 98%. The project was built using PyTorch (a convolutional neural network, and CUDA).
- Implemented a movie review sentiment analysis with a convolutional neural network, TensorFlow, Python, and Python Notebooks.
- Developed a Lego bricks identification system to identify using TensorFlow with Go language and OpenCV.
- Implemented cryptocurrency market prediction along with historical data of online trading using TensorFlow on the Go language.
Lead Data Scientist and Machine Learning Expert2018 - 2018Johnson & Johnson - Data Science
Technologies: TensorFlow, Python, Pandas, NumPy, Linear Regression, Logistic Regression, Data Modeling, Cleaning, Jupyter Notebooks, Artificial Intelligence, Machine Learning, Data Science, RedHat 7, Windows 10, Vagrant
- Led and created data pipelines, which used millions of data points, for the identification of the best strategies to increase the effectiveness of professional educational events (specifically those events for medical device training all across the USA and elsewhere).
- Verified the work done by another data science company in the domain of medical professional education events.
- Worked directly with principle scientists of Johnson and Johnson - Data Science in New York.
Lead Go Developer2018 - 2018Loom Network
- Built a Karma system for a decentralized crypto platform.
- Implemented a Sparse Merkle Tree.
- Developed a rate limiter for access control.
- Designed with Oracle for a Loomchain platform.
Freelance TensorFlow Expert2018 - 2018Ever AI (via Toptal)
- Worked for Ever AI, the world's leading face recognition technology company that raised a total of 30 million in funding. It implements face recognition at a planetary scale of 12 billion images.
- Was tasked to invent the fastest algorithm to identify the correct face using machine learning.
- Developed the fastest algorithm in less than half the time with a 99.81% accuracy.
Chief Scientist and Chief Technology Officer2015 - 2015Zidisha, Inc.
Technologies: Laravel, Propel, Vagrant, CSS3, Bootstrap, Sass, GitHub, Ubuntu Trusty64, PayPal, Stripe
- Built new features and functionalities for a website with Laravel, Propel Bootstrap, Beanstalk servers and Ubuntu Trusty64.
- Supported the entire back-end code and reviewed the front-end code that was done by other team members for further verification.
- Implemented automatic language translation for each new user.
- Worked as a remote engineer for a US-based company.
Founder and Lead Back-end Developer2013 - 2015Remarkin
Technologies: PHP, MN Framework, jQuery, Bootstrap, Responsive Design, MySQL, Design Patterns, C/C++, Windows Azure, Windows Service 2012, OpenCV, Artificial Neural Networks, Scala, Gamification
- Developed a video engagement prediction system with artificial neural networks, OpenCV, and Scala.
- Built a remote interactive C/C++ compiler with a TinyC compile and a GNU compiler.
Project Trainer2012 - 2013Aspire Institute
Technologies: PHP, MySQL, CSS, CSS3, HTML5, HTML, C, Advance C, C++, Object-oriented Programming
- Trained for a year for more than 150 students for their final year projects in the college.
- Coached for C/C++ language programming skills.
Web Developer2012 - 2013Cruxbot
- Built a Parallax website that represented artificial intelligence based company.
- Helped build an interface for the text summarization browser extension CruxLight.
Web Developer2011 - 2012Amitech
- Developed Picinchat.com and enabled it to create mega emoticons from user uploaded images. These emoticons were created using PHP, the Facebook API, and the GD library.
Freelance Developer2010 - 2011Self-employed
- Created a real-time chatting feature for a site with a real-time feed of a user typing on the other side.
- Developed a Flash-based cricket single player vs computer game.
- Worked on a tic-tac-toe human vs computer machine.
- Built a live video-streaming website with a screenshot for video scroll navigation.