Bhavana J

About Bhavana J

I am an AI/ML Engineer with 3 years of experience designing, building, and deploying machine learning, deep learning, and NLP solutions across healthcare, fintech, and enterprise domains. My expertise spans the full ML lifecycle—from data engineering and feature engineering to model development, optimization, deployment, and monitoring.I specialize in:Machine Learning & Deep Learning: TensorFlow, PyTorch, Scikit-learn, XGBoost, LightGBM, LSTMs, CNNs, Transformers (BERT, GPT, Hugging Face).NLP & Computer Vision: Text classification, medical coding automation, sentiment analysis, entity extraction, and computer vision using OpenCV and YOLO.MLOps & Deployment: MLflow, Airflow, Docker, Kubernetes, CI/CD (Azure DevOps, GitHub Actions), AWS SageMaker, GCP Vertex AI, Azure ML.Big Data & Cloud: Spark, Hadoop, Kafka, AWS (EC2, S3, Glue, Lambda), GCP (BigQuery), Azure (AKS).Visualization & Analytics: Tableau, Power BI, Python (pandas, matplotlib, seaborn).I am passionate about applying AI to solve real-world problems—from reducing hospital readmissions and accelerating medical claims, to fraud detection, recommendation systems, and time-series forecasting. I focus on building scalable, explainable, and production-ready AI systems that drive measurable business impact while ensuring fairness and compliance.Currently pursuing my Master’s in Computer Science at the University of Central Missouri, I bring both academic rigor and hands-on experience in AI/ML engineering, cloud platforms, and MLOps best practices. Open to opportunities in AI/ML Engineering, Data Science, Applied ML, and MLOps Engineering roles where I can contribute to building intelligent systems that deliver impact at scale.

Experience

1. Ai Ml Developer

   HCLTech

   Dec 2024 — Present

   Developed predictive models (XGBoost, Random Forest, Logistic Regression) using Python and Scikit-learn on patient EHR and claims data (~10TB), reducing 30-day hospital readmission by 18%, improving clinical intervention efficiency. Engineered data pipelines using PySpark and AWS Glue to ingest and transform multi-source structured/unstructured data; improved ETL throughput by 40% and ensured data freshness for model training workflows. Built and deployed NLP-based models using spaCy, BERT, and Transformers to extract ICD codes and key terms from physician notes, increasing automated medical coding accuracy by 22% and claim cycle speed by 3 days. Containerized ML models with Docker and deployed on AWS SageMaker endpoints via Lambda and API Gateway, enabling realtime fraud detection inference with latency under 200ms. Orchestrated model training pipelines using Apache Airflow and MLflow with integrated versioning, experiment tracking, and retraining triggers, reducing model drift and downtime by 45%. Conducted feature engineering using SQL, pandas, and domain-driven feature selection techniques, enhancing AUC-ROC of risk stratification models from 0.72 to 0.89. Implemented data quality checks and automated validations with Great Expectations, cutting preprocessing errors by 35% and supporting compliance for HIPAA and SOC2 requirements. Collaborated with cross-functional teams (Data Engineering, Product, Compliance) in Agile sprints, leading sprint demos and producing stakeholder documentation that improved model interpretability and regulatory audit readiness.

Education

• Sir C.R. Reddy College, Eluru

  Bachelor of Technology - BTech, Computer Science

  2019

• University of Central Missouri

  Master's degree, Computer Science