Data Science & ML Agent Skills

LangChain & LangGraph Architecture

Architects sophisticated LLM applications using LangChain 1.x and LangGraph for stateful agents, complex workflows, and advanced memory management.

RAG System Implementation

Builds sophisticated Retrieval-Augmented Generation (RAG) systems to ground LLM responses in proprietary data and external knowledge bases.

RLOO Reinforcement Learning

Implements Reinforcement Learning with Leave-One-Out (RLOO) estimation for stable policy optimization and reasoning model training.

Supervised Fine-Tuning (SFT) with Unsloth

Accelerates LLM instruction-tuning using Unsloth-optimized SFTTrainer for faster, memory-efficient model adaptation.

AI Agent Architect

Architects and implements autonomous AI agent systems using sophisticated planning, memory, and tool-integration strategies.

xAI Financial Intelligence & Data Integration

Integrates real-time xAI Grok sentiment with major financial APIs to provide a holistic view of market trends, price action, and fundamental health.

RAG Pipeline Implementation

Implements Retrieval-Augmented Generation (RAG) workflows to ground AI responses with external document context and reduce hallucinations.

Model Fine-Tuning & Training

Fine-tunes large language models using PyTorch, HuggingFace, and Unsloth to adapt AI behaviors to specific datasets and tasks.

HuggingFace Model Importer

Imports GGUF models from HuggingFace directly into Ollama for local inference and model management.

Transformer Architecture & Implementation

Provides technical blueprints and implementation patterns for the Transformer architecture to guide LLM development and fine-tuning.

Semantik Plugin Development

Builds custom plugins for the Semantik search engine to handle document ingestion, embeddings, and AI-powered reranking.

Optimized ML Inference

Accelerates machine learning inference using Unsloth and vLLM backends for 2x faster token generation.

LLM Evaluation with Evidently.ai

Evaluates LLM output quality and optimizes prompt templates using Evidently.ai metrics and LLM-as-a-Judge patterns.

Reward Model Training

Streamlines the development and training of reward models for RLHF pipelines and thinking quality scoring.

LangChain Framework

Builds sophisticated LLM applications using LangChain for prompt management, model chaining, and structured output parsing.

Auto-Claude Memory System

Implements a persistent knowledge graph memory system for Auto-Claude to retain context and learn patterns across development sessions.

LLM Project Development Methodology

Architects and optimizes LLM-powered applications using structured methodologies, pipeline design, and agent-assisted development patterns.

Model Quantization

Optimizes large language models for efficient inference and training by reducing memory footprint using advanced precision-shifting techniques like 4-bit and 8-bit quantization.

BDI Mental State Modeling

Transforms external RDF context into formal Belief-Desire-Intention (BDI) models to enable rational agency and explainable reasoning in AI agents.

Vision Model Fine-Tuning

Fine-tunes vision-language models like Pixtral and Ministral using Unsloth's FastVisionModel optimizations for faster training.

DPO Preference Optimization

Optimizes Large Language Models using Direct Preference Optimization to align behavior with preferred response pairs without explicit reward modeling.

PEFT & LoRA Fine-Tuning

Streamlines parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and Unsloth to optimize memory and training speed.

GRPO Alignment & RLHF

Implements Group Relative Policy Optimization for efficient LLM alignment and reinforcement learning from human feedback.

Context Engineering Fundamentals

Provides foundational expertise in context engineering to optimize AI agent performance and manage token usage effectively.

Memory Manager

Persists project knowledge and error-solution patterns across autonomous coding sessions to prevent repetitive mistakes.

xAI Grok Model Selector

Simplifies the selection and optimization of xAI Grok models for development tasks through detailed capability and cost analysis.

HiPerGator Multi-Group Conda Manager

Configures and manages multiple Conda environment locations across different research group storage allocations on the UF HiPerGator supercomputer.

Scientific Project Data Separation

Organizes scientific research repositories by decoupling core code from experimental data and notebook outputs.

Ollama Python Integration

Provides a clean, Pythonic interface for local LLM inference, chat completions, and model management using the official Ollama library.

Multi-Agent Architecture Patterns

Designs and implements sophisticated multi-agent systems using supervisor, swarm, and hierarchical patterns to solve complex context management challenges.