I build machine learning systems, deploy production-ready pipelines, and develop LLM/RAG-based intelligent applications. My experience spans fraud detection, healthcare predictive analytics, and enterprise-grade AI solutions.
- AI/ML Engineer with 3 years of hands-on experience in banking & healthcare
- Skilled in building end-to-end ML pipelines, deploying models to AWS, and tuning deep learning/LLM systems
- Experienced with PyTorch, TensorFlow, Scikit‑learn, Hugging Face, LangChain, and RAG architectures
- Passionate about MLOps, LLMs, and scalable cloud architectures
- Currently completing MS in Computer Science (May 2025)
End-to-end pipeline using PyTorch/Sklearn + AWS SageMaker. Includes:
- Feature engineering, ETL (Airflow/Glue), Snowflake integration
- Model retraining + MLflow versioning
- Drift monitoring + Power BI dashboards
🔗 Repo Coming Soon
TensorFlow/Keras deep-learning model for predicting patient risk.
- PySpark preprocessing of 20M+ EHR records
- BERT-based clinical NLP pipeline
- Flask API + ECS deployment + CloudWatch monitoring
🔗 Repo Coming Soon
Domain‑specific chatbot using:
- HuggingFace Transformers
- FAISS vector search
- LangChain agents
- Streamlit front‑end
🔗 Repo Coming Soon
Languages: Python, SQL, R, Java, Scala
ML/DL: PyTorch, TensorFlow, Keras, Scikit‑learn, XGBoost
NLP/LLM: Transformers, BERT, GPT, LangChain, RAG
Data Engineering: Pandas, NumPy, PySpark, Airflow, Kafka
MLOps: MLflow, Docker, Kubernetes, SageMaker, GitHub Actions, Jenkins
Cloud: AWS (S3, Lambda, ECS, Glue, SageMaker), GCP
Databases: Snowflake, PostgreSQL, MongoDB, Redshift
Visualization: Power BI, Tableau, Matplotlib
- Email: hemap0420@gmail.com
- LinkedIn: https://linkedin.com/in/hema-perumalla-27991237a
⭐ Thanks for visiting my GitHub! Feel free to explore my projects or reach out for collaboration.