Data Science & ML Agent Skills

AI Agent Architect

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

LLM Application Patterns

Implements production-ready architectures for LLM-powered applications, including RAG pipelines, agentic workflows, and LLMOps monitoring.

Academic Research Engineer

Implements high-performance software and complex algorithms with uncompromising scientific rigor and formal verification.

Voice AI Development

Builds high-performance, low-latency voice AI applications and real-time conversational agents using industry-leading providers.

Trading Predictor Agent

Predicts market movements and executes trades using sublinear algorithms and temporal advantage calculations to outpace traditional data transmission speeds.

Voice AI Development

Architects high-performance AI voice agents with optimized latency for natural, real-time human-AI conversations.

AI Product Engineering

Builds production-grade AI features using robust LLM integration patterns, structured output validation, and cost-effective prompt engineering.

Video Analysis Toolkit

Analyzes and extracts structured insights from video files using AI-powered understanding and timestamped key moment identification.

Academic Research Engineer

Implements high-performance software and complex algorithms with absolute scientific rigor and formal verification standards.

Professional Excel & Financial Modeling

Automates the creation, editing, and analysis of professional-grade Excel spreadsheets with industry-standard financial modeling practices.

AI Agents Architect

Designs and implements robust autonomous AI agents with sophisticated tool use, planning strategies, and multi-agent orchestration capabilities.

LLM Application Patterns

Provides production-ready architectural patterns for building robust LLM applications, covering RAG pipelines, autonomous agents, and LLMOps observability.

AI Agent Systems Architect

Architects and implements autonomous AI agent systems featuring robust tool use, memory management, and multi-agent orchestration.

LLM Application Patterns

Provides production-ready architectural patterns and implementation guides for building robust LLM applications, RAG pipelines, and AI agents.

LLM Prompt Caching

Optimizes LLM performance and reduces API costs by implementing advanced prefix caching, response caching, and Cache Augmented Generation strategies.

Prompt Engineering Expert

Optimizes AI performance and reliability through advanced prompting patterns like Few-Shot Learning and Chain-of-Thought reasoning.

Content-Hash File Caching

Implements path-independent, auto-invalidating file processing caches using SHA-256 content hashes for maximum performance.

Conversation Memory

Implements tiered memory systems for LLMs to maintain persistent context and entity-based knowledge across interactions.

LangGraph Agent Architect

Builds production-grade, stateful AI agents using the LangGraph framework for complex, multi-actor workflows.

Conversation Memory

Implements sophisticated persistent memory systems to help AI assistants retain context and user information across multiple interactions.

Spark Optimization

Optimizes Apache Spark data processing jobs through advanced partitioning, memory management, and shuffle tuning.

Conversation Memory

Implements persistent, multi-tiered memory systems to enhance LLM context retention and entity tracking across interactions.

BayesFlow Model Validation

Validates BayesFlow neural posterior estimators using simulation-based calibration (SBC) and comprehensive diagnostic metrics.

AI Product Architect

Architects and implements high-quality, defensible AI-powered products by bridging LLM APIs with specialized domain logic and robust cost controls.

Agent Memory Architectures

Architects robust memory systems for intelligent agents using short-term, long-term, and episodic retrieval patterns.

BayesFlow Adapter Orchestrator

Streamlines the creation and debugging of data preprocessing pipelines for BayesFlow simulation-based inference.

BayesFlow Keras-Ops

Standardizes tensor operations using Keras 3 backend-agnostic math to ensure compatibility across PyTorch, JAX, and TensorFlow.

BayesFlow Packaging Specialist

Enforces best practices for BayesFlow extension packages, including src-layout, dependency management, and API exports.

Semantic Vector Embeddings

Empowers Claude with high-performance vector embeddings, HNSW indexing, and persistent semantic search capabilities.

Fine-Tuning Expert

Optimizes and adapts foundation models through parameter-efficient fine-tuning (PEFT), dataset preparation, and production-ready ML workflows.