I am a Senior AI / ML Engineer with over 8 years of experience specializing in machine learning and artificial intelligence, particularly within healthcare applications. Throughout my career, I have led the development of deep learning pipelines for medical imaging, positively impacting over 2,000 patients and significantly reducing manual review times by 35%. My expertise includes building scalable machine learning models using Python and TensorFlow, as well as designing real-time inference systems that support hospital networks.
I have a strong background in implementing MLOps frameworks, which has saved engineering teams 35 to 50 hours of manual deployment effort each month. My work involves architecting and maintaining AI services with Docker and Kubernetes, ensuring high availability and reliability. I am experienced in developing clinical NLP pipelines using transformer architectures like BERT and BioBERT, improving efficiency in medical entity recognition by 40%.
My role often requires orchestrating large-scale ETL workflows, integrating vast healthcare datasets from EHR systems such as Epic and Cerner, and deploying scalable ML infrastructure on AWS SageMaker. I have successfully led model validation and monitoring initiatives to ensure fairness and regulatory compliance, reducing false positives by 37% through automated alerting systems.
I am proficient in a wide range of programming languages including Python, Go, and JavaScript, and skilled in AI frameworks such as PyTorch, TensorFlow, and Hugging Face. My experience extends to cloud platforms like AWS, Azure ML, and Google Cloud AI Platform, as well as data engineering tools including Apache Spark and Kafka.
I am passionate about leveraging AI to improve healthcare outcomes and streamline clinical workflows. My projects include developing clinical risk prediction platforms and medical imaging classification systems that have enhanced diagnostic accuracy and operational efficiency. I am committed to continuous learning and applying cutting-edge AI technologies to solve real-world problems in healthcare.
Focused on machine learning, artificial intelligence, and distributed systems.
Built scalable machine learning models utilizing Python and TensorFlow for clinical risk predictions, impacting over 2,000 patients. Directed design and deployment of neural network pipelines for CT and MRI image analysis. Architected and maintained real-time inference systems using Docker and Kubernetes. Implemented MLOps frameworks with MLflow and automated CI/CD pipelines, reducing deployment time and manual effort by 35โ50 hours monthly. Enhanced predictive analytics systems improving medical coding efficiency by 40%.
Engineered predictive models using gradient boosting and ensemble techniques, reducing patient readmission rates by 15%. Developed clinical NLP pipelines with transformer architectures (BERT, BioBERT) improving efficiency by 40%. Orchestrated large-scale ETL workflows integrating 50+ TB healthcare data from EHR systems using Apache Spark and cloud data lakes. Delivered scalable ML infrastructure on AWS SageMaker supporting hospital-wide analytics dashboards. Led model validation and monitoring, reducing false positives by 37% through automated alerting.
Improved treatment recommendations by developing AI-powered systems using XGBoost, LightGBM, Random Forest, and PyTorch, achieving 15-20% AUC improvement. Enhanced ICU resource management with ARIMA, Prophet, and LSTM models, improving demand prediction accuracy by 20-25%. Optimized clinical data pipelines reducing manual processing time by 10 hours per week. Maintained API performance with secure REST APIs built in Flask for real-time model inference.
Jobicy
614 professionals pay to access exclusive and experimental features on Jobicy
Free
USD $0/month
For people just getting started
Plus
USD $8/month
Everything in Free, and: