🔍 I am a AI Research Engineer/Machine Learning Engineer with a strong foundation in computational modeling, deep learning architectures, and scientific data analysis. I specialize in building data-driven solutions for complex physical systems, especially focusing on battery degradation modeling and predictive analytics.
⚡ My research and development interests include:
- Diffusion Models for generative tasks on time-series and scientific data
- Variational Autoencoders (VAEs) for representation learning and anomaly detection
- Autoregressive Models for sequential latent vector prediction tasks
- Transformer Architectures for long-range dependency modeling in time-series
- Physics-Informed Machine Learning for better modeling of real-world systems
- Battery Health Forecasting using machine learning and AI-driven simulations
🛠️ Technical Skills:
- Programming: Python (advanced), C++, SQL
- Frameworks/Libraries: PyTorch, TensorFlow, Scikit-learn, FastAPI
- Machine Learning Expertise: Supervised, Unsupervised, and Generative Modeling
- Database Management: PostgreSQL, MongoDB
- DevOps & Tools: Linux, Docker, Git, AWS Cloud Services
- Scientific Computing: Numerical methods, PDE Solvers, Statistical modeling
📚 Current Focus Areas:
- Building Generative Models tailored for 1D battery voltage evolution data
- Developing robust battery health prediction pipelines based on deep generative models
- Exploring autoregressive transformers for sequence modeling in latent space
- Advancing skills in MLOps and model deployment for large-scale data solutions.
🤝 I'm looking to collaborate on projects related to:
- Battery lifecycle prediction and digital twins
- Generative AI for scientific and industrial applications
- Time-series modeling with cutting-edge deep learning techniques
📂 Explore my portfolio: Visit my website
📫 Connect with me: rvraghvender@gmail.com
