Data Science & ML Agent Skills

NeMo Guardrails Safety Alignment

Implements programmable safety rails and runtime validation for LLM applications using NVIDIA's NeMo Guardrails framework.

SentencePiece Tokenization

Implements language-independent subword tokenization using BPE and Unigram algorithms for robust NLP model training and inference.

SAELens Mechanistic Interpretability

Decomposes neural network activations into interpretable, sparse features using SAELens for deep mechanistic interpretability research.

SGLang Inference Serving

Optimizes LLM serving and structured data generation with RadixAttention prefix caching for high-performance agentic workflows.

Instructor - Structured Data Extraction

Extracts and validates structured data from LLM responses using Pydantic for reliable, type-safe outputs and automatic retries.

HuggingFace Accelerate Distributed Training

Simplifies PyTorch distributed training across multiple GPUs, TPUs, and nodes with minimal code changes and a unified API.

OpenRLHF Model Training

Deploys and manages high-performance RLHF training pipelines for large-scale language models using Ray and vLLM acceleration.

Constitutional AI Safety Alignment

Implements Anthropic's Constitutional AI method to train harmless AI models through self-critique and reinforcement learning from AI feedback.

HQQ Model Quantization

Quantizes Large Language Models to ultra-low bit precision without requiring calibration datasets for efficient inference and fine-tuning.

Slime RL Post-Training

Scales LLM post-training via reinforcement learning by integrating Megatron-LM training with high-throughput SGLang inference.

NeMo LLM Evaluator

Evaluates Large Language Models across 100+ industry-standard benchmarks using NVIDIA's enterprise-grade containerized architecture.

CrewAI Multi-Agent Orchestration

Orchestrates autonomous teams of specialized AI agents to collaborate on complex, multi-step tasks and production workflows.

Stable Diffusion Image Generation

Generates high-quality images from text and performs advanced image-to-image transformations using the HuggingFace Diffusers library.

Long Context Transformer Engineering

Extends Transformer model context windows using advanced positional encoding and interpolation techniques like RoPE, YaRN, and ALiBi.

Chroma Vector Database

Manages high-performance vector embeddings and metadata for RAG applications and semantic search using the open-source Chroma database.

LM Evaluation Harness

Evaluates Large Language Models across 60+ academic benchmarks using standardized prompts and metrics for reproducible research.

BLIP-2 Vision-Language

Implements state-of-the-art vision-language pre-training to enable high-quality image captioning and visual question answering within AI workflows.

NVIDIA TensorRT-LLM Optimization

Optimizes Large Language Model inference for maximum throughput and ultra-low latency on NVIDIA GPUs.

Sentence Transformers Embeddings

Generates high-quality sentence, text, and image embeddings for RAG, semantic search, and clustering using state-of-the-art transformer models.

Weights & Biases MLOps

Integrates Weights & Biases into your workflow to track machine learning experiments, visualize training metrics, and manage model artifacts in real-time.

Pyvene Causal Interventions

Facilitates causal interventions on PyTorch models using a declarative framework for mechanistic interpretability experiments.

FAISS Vector Search

Implements efficient similarity search and clustering for dense vectors at scale using Facebook AI's high-performance library.

Model Merging & Fusion

Combines multiple fine-tuned AI models into a single high-performance model without requiring additional training or expensive GPU resources.

Mamba Architecture Guide

Implements and optimizes Selective State Space Models (SSM) for high-performance sequence modeling and long-context AI applications.

torchforge RL Training

Implements PyTorch-native agentic reinforcement learning workflows using Meta's torchforge library for scalable algorithm experimentation.

Pinecone Vector Database

Integrates Pinecone's managed vector database to power high-performance RAG, semantic search, and recommendation systems.

Ray Data Scalable Processing

Facilitates high-performance distributed data processing and streaming for large-scale machine learning workloads.

DSPy AI Programming & Optimization

Build and optimize complex AI systems using declarative programming instead of manual prompt engineering.

MLflow MLOps Manager

Manage the complete machine learning lifecycle including experiment tracking, model versioning, and deployment using the MLflow framework.

LlamaIndex RAG Framework

Builds sophisticated RAG applications by connecting LLMs to private data through advanced indexing and retrieval patterns.