Sam. . Email & Phone Number

New York, Ny, Us

Worked as an AI/ML Engineer, contributing to the development and optimization of AI-driven solutions for a digital banking platform, enhancing customer experiences with secure and intelligent services. Leveraged Python for back-end development and utilized machine learning frameworks such as TensorFlow and PyTorch for model implementation. MongoDB, a NoSQL database, was used for handling large datasets, and AWS services were employed for scalable deployment and data processing. The project resulted in more intelligent, secure, and efficient banking operations.Designed and deployed AI models for fraud detection and customer behavior analysis, utilizing machine learning algorithms and predictive modeling techniques.Developed RESTful APIs to seamlessly integrate AI models with the front-end and back-end systems, enabling real-time predictions and data insights.Implemented secure authentication mechanisms using OAuth and enhanced data privacy with AI-driven anomaly detection techniques.Engineered scalable machine learning pipelines using TensorFlow, Python, and AWS Lambda to automate model training, testing, and deployment.Automated model training workflows with CI/CD pipelines, ensuring smooth integration and continuous delivery of AI models, while using pytest for validating data pipelines.Designed microservices architectures for AI model deployment using Kubernetes and leveraged AWS services such as EC2 for scalable computing, S3 for secure data storage, and RDS for managing relational data.Optimized data handling and performance by integrating caching strategies with Amazon ElastiCache and implemented Elastic Load Balancing (ELB) to ensure efficient distribution of workloads.Developed and deployed NLP models to analyze customer feedback and sentiment, improving customer service efficiency.

As a Machine Learning Engineer, contributed to improving Amazon Rekognition's API and Python SDK integration, focusing on real-time facial recognition, video analysis, and activity detection. Utilized AWS services like S3, Lambda, and Kinesis to enable scalable, cost-efficient solutions for facial recognition and image/video analysis in various industries such as security, retail, and content moderation.• Developed and optimized machine learning models for real-time facial recognition and video analysis using Python and AWS Rekognition, improving accuracy and performance for various applications like security and content moderation.• Built and integrated RESTful APIs for seamless communication between front-end interfaces (React.js, Vue.js) and machine learning models, ensuring smooth data flow and real-time analytics for users.• Utilized AWS Lambda to create serverless functions that enable event-driven image and video processing workflows, ensuring scalability and cost-efficiency in large-scale machine learning deployments.• Developed and fine-tuned ML models for facial recognition using Python, focusing on emotion detection, age prediction, and facial landmark detection for improved real-time analysis.• Designed and developed scalable backend systems for real-time video analysis, utilizing AWS EC2, Lambda, and S3 to store and process large media files in an efficient and cost-effective manner.• Worked with PostgreSQL to store and retrieve metadata linked to analyzed images and videos, ensuring smooth integration with machine learning models for ongoing learning and prediction tasks.• Automated data pipelines and processing workflows using Python scripts, enhancing data handling efficiency for large video surveillance and content management systems.• Implemented real-time video stream processing using AWS Kinesis to improve the speed and efficiency of live video feeds, enabling quick object detection and activity recognition for various ML tasks.

Worked on developing a Payment Gateway system, utilizing Python for backend logic, Django and Flask for streamlined Python-based application development, and HTML/CSS/JavaScript for frontend development, with React.js for interactive user interfaces. Integrated AWS services, API Gateway for building and managing APIs, Lambda for serverless compute, DynamoDB for NoSQL database storage. This comprehensive solution facilitated secure and seamless payment processing.· Ensured smooth backend service integration by collaborating with frontend developers to create interactive user interfaces using HTML, CSS, JavaScript, and React.js.· Integrated PayPal for payment gateway functionality, facilitating secure and seamless payment processing for users.· Ensured data security by implementing HTTPS for secure communication between clients and servers.· Proficiently utilized AWS cloud services, including EC2, S3, Lambda, and RDS, to architect, develop, and deploy scalable and resilient Python-based applications.· Effectively administered MongoDB databases, ensuring optimized performance, data integrity, and reliability for Python-based applications.· Proficiently designed and developed microservices architecture using Python, facilitating modular and scalable application development.· Implemented end-to-end CI/CD pipelines using Jenkins and Kubernetes for Python applications, automating build, test, and deployment processes to achieve continuous integration and delivery.· Leveraged Prometheus for monitoring and logging, providing real-time visibility into system performance and health metrics.· Created a cross-training program ensuring FOH staff members were able to perform confidently and effectively in all positions.