Python Developer | Machine Learning Engineer

I have extensive experience in Python, with a strong focus on machine learning applications and backend development using Django. I have used Python libraries such as TensorFlow, PyTorch, and OpenVINO to develop, train, and deploy machine learning models for tasks like object detection, image classification, and real-time data processing. I have also integrated these models into scalable systems, leveraging cloud platforms like Google Cloud and Azure for model training and deployment. In addition to machine learning, I have developed backend applications using Django, designing and implementing RESTful APIs and handling database management with Django’s ORM. I utilize Jupyter Notebooks for model experimentation and optimization, and I’m skilled in data manipulation and preparation with libraries like Pandas and NumPy.

I have experience in developing and deploying web applications using Django, a powerful Python-based framework. My work includes designing scalable backend architectures, creating RESTful APIs, and integrating them with front-end applications. I have also utilized Django's ORM for efficient database management and implemented user authentication, authorization, and role-based access controls. Additionally, I have worked on optimizing application performance, handling asynchronous tasks with tools like Celery, and deploying Django applications in cloud environments for scalability and reliability.

I have extensive experience in implementing machine learning, IoT systems, and cloud-based solutions, focusing on both model training and deployment. In my machine learning work, I have trained YOLO models for object detection, optimized hyperparameters, and managed training on Tesla T4 GPUs with CUDA. I have utilized platforms such as TensorFlow, ONNX Runtime, and OpenVINO for efficient model development and inference, integrating these models into applications for real-time processing. My work also involves extensive experience with IoT cameras and IoT systems, where I have coded service applets to enable seamless integration with machine learning models for tasks such as surveillance, monitoring, and real-time data processing. Additionally, I have prepared high-quality datasets through data preparation, augmentation, and annotation. In my cloud-based solutions, I have leveraged Azure to create scalable and reliable applications. Using Azure Functions, I designed workflows to process queue-based requests sequentially, efficiently managing API throttling challenges. I have also integrated Azure Queue Storage for asynchronous message handling and applied strategies for high-traffic optimization. Combining my expertise in machine learning, IoT systems, and Azure, I have developed innovative solutions that bridge cloud and AI technologies.

I have been using Azure to implement cloud-based solutions, focusing on serverless architectures. My experience includes designing and implementing Azure Functions to process queue-based requests sequentially, effectively managing API throttling challenges. I have also integrated Azure Queue Storage for efficient message handling in asynchronous workflows and applied strategies to handle high-traffic scenarios while optimizing resource utilization. Additionally, I have leveraged Azure's robust platform for backend development, ensuring reliability and scalability. Moving forward, I aim to deepen my expertise in Azure's capabilities, particularly in optimizing performance and cost efficiency for serverless solutions.

I have experience leveraging Google Cloud's Vertex AI to train machine learning models, utilizing the platform's robust infrastructure for model development and deployment. In this environment, I have integrated Google Cloud Storage for efficient data handling and used Jupyter Notebooks for model experimentation and training. This setup has enabled me to streamline workflows and manage large datasets while taking advantage of the scalability and performance provided by Vertex AI. Moving forward, I aim to further explore advanced features within Vertex AI and Google Cloud to optimize model training and deployment pipelines.

I have been using Nest.js for backend web development, leveraging its powerful features to build scalable and maintainable applications. With Nest.js, I have designed and implemented RESTful APIs, structured backend services using a modular approach, and managed complex business logic through its efficient dependency injection system. I have also integrated Nest.js with databases using TypeORM and Prisma for seamless data management, and utilized tools like GraphQL for more flexible data querying. My experience with Nest.js allows me to develop high-performance, reliable backend systems that are easily extensible and maintainable. Moving forward, I aim to continue building expertise in Nest.js, especially in optimizing performance and scaling applications to handle growing demands.

I have experience using Next.js within a monorepo setup, enabling me to manage multiple projects and shared resources in a single codebase efficiently. By organizing frontend and backend components into distinct packages, I have streamlined the development process, improved code reusability, and ensured consistency across different parts of the application. In this monorepo environment, I have used tools like Yarn Workspaces and Lerna to manage dependencies and optimize build processes. Next.js, combined with a monorepo, allows for easy deployment and scaling of both client-side and server-side applications. This setup has enhanced collaboration across teams, making it easier to maintain large applications while ensuring smooth integration between different services. Moving forward, I aim to continue refining my expertise in managing Next.js applications within monorepos, improving build optimization, and enhancing team collaboration in large-scale projects.

I have experience working with AWS to build scalable, high-performance applications and services. My work includes utilizing AWS services such as EC2 for computing, S3 for storage, Lambda for serverless computing, and RDS for managed database solutions. I have also worked with DynamoDB for NoSQL database management, enabling efficient, high-availability data storage and retrieval. Additionally, I have used AWS tools like CloudFormation for infrastructure as code and CloudWatch for monitoring and logging to ensure the reliability and scalability of applications. Moving forward, I aim to expand my expertise in AWS services like ECS, EKS, and further optimize cloud architectures for performance and scalability.