3. Data, Science & AI

Transforms business requirements into logical data models through entity extraction, relationship analysis, and normalization decisions for database schema design.

Provides production-grade solutions for PostgreSQL challenges including query optimization, concurrency management, and zero-downtime migrations.

Constructs and manages data pipelines, ETL processes, and data warehousing solutions using tools like Airflow and Spark.

Provides SQL database best practices for query optimization, indexing, and schema design.

Configures GA4 event tracking with standardized patterns and taxonomy for user interaction and e-commerce analytics implementation.

Enables creation and management of LangChain agents, RAG pipelines, and tool-calling workflows for LLM applications.

AI image generation and editing using the Gemini model for creating and modifying visual content.

Provides 1D and 2D data interpolation using SciPy (CPU) and JAX/Interpax (GPU/differentiable).

Expert in orchestrating deep learning model training, validation, testing, and dataset splitting with predefined model structures.

Guide for building, training, and managing neural networks with Flax NNX, including model definition and state handling.

Provides utilities for vector database operations including embedding storage, semantic search, and RAG retrieval.

Optimizes AI agent context to reduce token costs and manage context limits efficiently.

Provides option pricing models including Black-Scholes, Greeks calculation via auto-differentiation, and exotic options analysis.

Provides essential tools for JAX, covering core concepts, transformations, ML specifics, control flow, and parallelism in machine learning.

Solves common SQLite challenges in embedded/edge deployments including connection handling, database locking, and schema modifications.

Provides high-performance data manipulation using Polars, including lazy API, data wrangling, and aggregation operations.

Expert in designing deep learning model architectures, including network structures, module division, data flow, and loss functions for AI applications.

Manages a dynamic AI skill learning system with pattern recognition, preference learning, and version control capabilities.

Provides machine learning capabilities including classification, regression, clustering, and model evaluation using scikit-learn.

Enables creation of data visualizations using Matplotlib, Plotly, and Seaborn for charts, graphs, and interactive plots.

Solves linear systems (Ax=b) using NumPy, JAX, PyTorch, and Lineax for dense, sparse, and tridiagonal matrices.

Enables implementation of agent memory systems, including knowledge graphs, entity tracking, and cross-session state persistence using vector stores.

Enables statistical modeling, A/B testing, and predictive analytics using pandas and scikit-learn for data-driven insights.

Provides scientific computing utilities for astronomy, bioinformatics, symbolic math, and statistics using Python libraries like astropy and sympy.