● Finetune and Deploy Local Large Language model for Generalized Document extraction task and for Data validation tasks.● Develop Application to extract Data From Images/Documents using OCR , LangChain and local LLMs for- CIB Report Analyzer- Bank Statement Analyzer● Develop Application to Match Faces using Face Recognition Models- Curate Dataset to Fine Tune Models- Write various Classifier Code to Fine Tune Face Recognition Model according to the accuracy… Show more ● Finetune and Deploy Local Large Language model for Generalized Document extraction task and for Data validation tasks.● Develop Application to extract Data From Images/Documents using OCR , LangChain and local LLMs for- CIB Report Analyzer- Bank Statement Analyzer● Develop Application to Match Faces using Face Recognition Models- Curate Dataset to Fine Tune Models- Write various Classifier Code to Fine Tune Face Recognition Model according to the accuracy requirements of the application.- Write Test and Metrics Code to Evaluate Model Performance and Accuracy● Develop RPA using Selenium to Automate Tasks and Scrap Data Show less

● Evaluation of trained model performance using pytorch and tensorflow● Deployment of model that process 360° image with GPU. Using Docker,Docker Compose, Nginx and flask. ● Resource optimization to improve result response time for 360° Image● Model and server resource monitoring using Grafana, Prometheus and node-exporter.● Rest API endpoint creation for parallel processing of queued 360° image with deployed models.

● Creating custom Neural Network Architecture forsupervised, semi-supervised Deep Learning Models usingPyTorch and Tensorflow● Writing Metric Evaluation code to quantify modelperformance and accuracy● Curating Dataset by reviewing, modifying andrestructuring so that it can be properly fed as input intocustom neural network model● Write code for feature engineering by augmenting the dataset● Hyperparameter tuning to improve accuracy●Deploy Machine learning… Show more ● Creating custom Neural Network Architecture forsupervised, semi-supervised Deep Learning Models usingPyTorch and Tensorflow● Writing Metric Evaluation code to quantify modelperformance and accuracy● Curating Dataset by reviewing, modifying andrestructuring so that it can be properly fed as input intocustom neural network model● Write code for feature engineering by augmenting the dataset● Hyperparameter tuning to improve accuracy●Deploy Machine learning models on Mobile Devices(Android) Show less

● Real time Video processing from IP Camera with OpenCV and python● Creating Multiple Face Tracker with OpenCV● Training Face Recognition models with Convolutional Neural Network (CNN) using Tensorflow● API endpoint Creation for analytics data● User Auth UI Design and Implementation● Docker deployment of python based image processing server in Google Cloud Platform(GCP)● Training Number Plate Detection and recognition models with Deep Neural Network(DNN)

● Data Modeling and Database design● Augmenting Field level data collection into database systems● Real Time data processing and analytics

● I was responsible for planing , organising and controlling events , seminars, workshop and training session create a atmosphere of learning in the field of Robotics in Bangladesh. ● i have organized some national events Such as PathFinder(Line Follower Robot) Competition and ROBUFest'16.● As part of our Research Project i have worked in a Mars Rover Competition called Mongol Tori as a lead Software engineer.