3. Data, Science & AI

Enables comprehensive evaluation of LLM applications through automated metrics, human feedback, and benchmarking to assess AI performance and quality.

Transforms raw data into analytical assets via ETL/ELT pipelines using dbt, Airflow, and Python data tools.

Fine-tunes large language models using reinforcement learning for instruction tuning, preference alignment, and reward optimization via HuggingFace Transformers.

Builds Retrieval-Augmented Generation (RAG) systems using vector databases and semantic search for knowledge-grounded LLM applications and document Q&A.

Optimizes existing AI prompts to reduce token consumption and improve output success rates for LLM interactions.

Engineers effective LLM prompts using zero-shot, chain-of-thought, and structured output techniques to ensure reliable AI application outputs.

Guide for designing multi-agent architectures, orchestration patterns, and collaboration strategies in AI systems.

AI-driven system and user flow optimization guide featuring bottleneck detection and performance enhancement strategies.

Generates optimized data visualizations including bar charts, line graphs, and scatter plots based on data structure analysis for clarity and insight.

Provides best practices for Hugging Face Transformers including model loading, tokenization, fine-tuning, and inference optimization for NLP tasks.

Automates strategy parameter optimization by iteratively running backtests, analyzing win rate and profit, and selecting configurations meeting criteria.

Designs and validates digital filters (FIR/IIR) in MATLAB for signal cleaning, interference removal, and frequency-specific filtering.

Runbook for executing and analyzing 4-hour backtests of the Vegas trading strategy, including metric queries and configuration updates.

Manages agent memory using CoALA cognitive architecture, enabling context retention, recall, and forgetting during interactions.

Provides expert guidance on PostgreSQL database features, including complex queries, JSON handling, full-text search, and performance optimization.

Guides creation of Model Context Protocol (MCP) servers enabling LLMs to securely interact with external APIs using Python or TypeScript.

Guides users on implementing data visualizations with uCharts, covering chart types, configuration, and platform integration.

Provides guidance for creating, configuring, and interacting with ECharts visualizations to effectively display and analyze data.

Guides users in generating AI images with Stable Diffusion, covering model configuration, prompt engineering, and parameter tuning.

Offers expert guidance on MongoDB operations including document manipulation, query optimization, aggregation pipelines, and schema design best practices.

Provides expert guidance on Redis data structures, commands, pub/sub, persistence, clustering, and caching patterns for efficient data management.

Guides Spring AI integration for AI models, RAG applications, and vector stores in Java-based AI-powered applications.

Guides users in database connections, SQL execution, data management, and administration using DBeaver.

Provides expert guidance on MySQL database management, including SQL queries, schema design, and performance optimization.