Computational Mathematics/Mathematics focused on probabilistic modeling, stochastic systems, and machine learning architectures.

I work at the intersection of applied probability, statistical learning, and computational methods for complex systems.

• Stochastic Systems:
  Probability theory, mathematical statistics, and discrete/continuous-time stochastic processes with applications to real-world data modeling.

• Quantitative Modeling:
  Statistical inference, spatio-temporal data analysis, and probabilistic forecasting of structured event processes.

• Computational Mathematics:
  Translating mathematical models into efficient, modular, and numerically stable implementations.

seismic-probabilistic-modeling

EarthquakeNet — end-to-end probabilistic pipeline for seismic event modeling.

• Hybrid DL + statistical framework for modeling earthquake occurrence
• Count modeling via Negative Binomial / Poisson process formulations
• Spatio-temporal feature engineering on USGS data
• Calibration of probabilistic outputs under noisy observational regimes

Keywords: Stochastic Processes, Count Models, Spatial-Temporal Systems, Statistical Learning
Stack: Python, NumPy, SciPy, PyTorch, Matplotlib

llm-longform-video-research

End-to-end system for automated long-form content generation and multimodal pipeline orchestration.

• Asynchronous data ingestion and processing pipelines
• LLM-driven narrative structuring and content synthesis
• Text-to-speech integration and multimodal assembly
• Automation of research-to-content workflows

Keywords: Systems Design, Async Pipelines, LLM Engineering, Multimodal AI
Stack: Python, Asyncio, APIs, System Integration

• Real Analysis & Calculus
• Measure Theory
• Probability Theory & Mathematical Statistics
• Stochastic Processes & Time Series Analysis
• Linear Algebra & Functional Analysis
• Optimization Theory
• Numerical Methods
• General Topology

• Languages: Python, C++, SQL, Bash, Java
• ML & Scientific Computing: PyTorch, NumPy, SciPy, Pandas

• Environments: Vim, Cursor, Prism
• Documentation: LaTeX, Markdown

My work is grounded in a probability-first view of complex systems, where uncertainty is not treated as noise, but as a fundamental object of study.

I am particularly interested in stochastic processes, probabilistic modeling, and how mathematical structure emerges in systems driven by randomness.

Rather than focusing purely on deterministic or black-box learning approaches, I aim to understand and model the underlying generative mechanisms of data through rigorous probabilistic frameworks.

This includes connections between:

• stochastic processes and time-evolving systems
• probabilistic inference and statistical learning
• and computational implementations of mathematical models

In the long term, my direction aligns with areas where probability, optimization, and computation intersect — including quantitative modeling, high-frequency stochastic systems, and research-driven machine learning approaches used in quantitative finance and related fields.

The goal is to build a consistent bridge between:

• rigorous probability theory
• computational mathematics
• and modern data-driven modeling