● Developed and deployed scalable microservices using FastAPI and Go/Golang, improving the system's response time by 30% for real-time image processing tasks in pathology.● Designed and implemented robust RESTful APIs using Django and Spring, enabling seamless integration between the frontend (React TypeScript) and backend services, enhancing user experience for clinical decision support tools.● Orchestrated cloud-native applications on AWS using services such as Lambda, EC2, and S3, resulting in a 25% reduction in infrastructure costs and improved reliability for machine learning model deployments.● Led the migration of monolithic applications to microservices using Python (Django) and Go, improving the system's fault tolerance and maintainability, which decreased downtime by 40%.● Built and optimized pathology data pipelines using AWS SQS, SNS, and Django, enabling real-time data ingestion and processing, increasing throughput by 50% for large-scale medical images.● Collaborated with cross-functional teams to implement a responsive frontend using React TypeScript, ensuring accessibility and improving UI performance for data-heavy visualizations used by pathologists.● Automated CI/CD pipelines using AWS CodePipeline and Docker, streamlining the deployment process for both Python/Django and Java/Spring services, reducing deployment time by 60%.● Fine-tuned pre-trained models such as BERT and GPT for specific medical applications, enhancing the performance of NLP tasks like entity recognition and text classification in clinical data.● Utilized TensorFlow and PyTorch frameworks to build, train, and validate machine learning models, ensuring robust and scalable solutions for pathology applications.