3. Data, Science & AI

Provides methodology for A/B testing and content experimentation to optimize content through data-driven analysis and statistical validation.

Expert PostgreSQL database optimization, including query tuning, indexing strategies, replication setup, and connection management.

Expert in Vercel AI SDK v5 for building and optimizing AI applications, handling streaming, model integration, and production patterns.

Expertise in MongoDB database design, performance tuning, and scalability strategies including aggregation pipelines, sharding, and indexing for optimal NoSQL data management.

Efficiently handles pandas DataFrame operations including data cleaning, aggregation, merging, and time series analysis with performance optimization.

Builds and manages end-to-end machine learning pipelines including training workflows, feature storage, and experiment tracking.

Architects RAG systems with vector databases for semantic search and context augmentation in AI applications.

Expert guidance for fine-tuning large language models, optimizing performance, and preparing datasets for task-specific adaptation.

Builds and optimizes Apache Spark applications for distributed data processing, including DataFrame API, Spark SQL, and streaming analytics.

Optimizes PostgreSQL performance through query analysis, replication configuration, JSONB operations, and VACUUM tuning.

Optimizes SQL queries and database schemas, focusing on performance tuning, complex queries, and indexing strategies.

Designs optimized prompts for LLMs, implements techniques like chain-of-thought, and builds evaluation frameworks to enhance model performance.

Analyzes slow queries and execution plans to optimize database performance through index design, query rewrites, and configuration tuning.

Builds and trains neural networks using TensorFlow for machine learning applications.

Creates optimized data pipelines for TensorFlow models using tf.data API to streamline data loading and transformation.

Deploys and serves TensorFlow machine learning models for production inference.

Calibrates conversational AI in real-time for domain-specific accuracy, avoiding generic responses and ensuring context-aware interactions.

Selects language frequencies to engineer specific emergent conditions through AI-driven linguistic patterns.

Provides comprehensive SQL patterns for common operations and migrations across PostgreSQL, MySQL, and SQLite.

Enables persistent context across user sessions by compressing and recalling interaction patterns, enhancing AI agent adaptability and learning.

Coordinates multi-agent systems to achieve collective intelligence and emergent behaviors in AI applications.

Activates Pattern Space layers to enable structured navigation within a skill-based AI system.

Creates, validates, and packages AI agent capabilities using the agentskills.io standard for cross-agent portability and discoverability.

Builds AI applications using Azure AI Projects SDK, enabling agent creation, evaluation, and management of AI resources like datasets and deployments.