Browse Skills

Designs automated machine learning pipelines for model selection, hyperparameter optimization, and neural architecture search. Covers AutoML frameworks (Optuna, Ray Tune, Auto-sklearn), search strategies, and production integration.

Design and implement safety, quality, and compliance guardrail systems for LLM-powered applications, covering input validation, output screening, prompt injection defense, PII protection, and regulatory compliance mapping.

Designs comprehensive LLM prompt evaluation frameworks with tailored metric suites, automated eval pipelines, A/B testing methodology, red-teaming protocols, and regression detection systems using industry-standard tools like RAGAS, DeepEval, and promptfoo.

Designs comprehensive evaluation frameworks for LLM and AI systems, combining automated metrics (BLEU, ROUGE, BERTScore), LLM-as-judge patterns (G-Eval), RAG evaluation (RAGAS), standard benchmarks (MMLU, HumanEval), safety evaluations, and A/B testing methodologies into production-ready evaluation pipelines.

Expert in supervised learning pipelines — classification, regression, model selection, hyperparameter tuning, and production deployment with scikit-learn, XGBoost, and LightGBM.

Designs privacy-preserving distributed machine learning systems using federated learning. Covers federated averaging, differential privacy, secure aggregation, communication efficiency, and compliance with privacy regulations.

Conducts comprehensive bias audits and ethical assessments of AI/ML systems, applying fairness metrics, regulatory frameworks (NIST AI RMF, EU AI Act), and structured impact assessments to identify and mitigate algorithmic harms.

Master XGBoost for tabular data problems including hyperparameter optimization, feature engineering, SHAP-based interpretability, and production deployment with drift monitoring.

Expert guidance on designing, building, and querying knowledge graphs using ontology engineering, graph databases, NLP-based construction pipelines, and LLM/GraphRAG integration patterns.

Build production-grade AI-powered features using the Vercel AI SDK with streaming responses, structured outputs, tool calling, and multi-provider support in Next.js applications.

Designs, builds, and validates high-quality training datasets for LoRA fine-tuning of large language models, applying data-centric AI principles and instruction-tuning best practices to maximize model performance per training example.

Design and implement machine learning-based lead scoring systems that predict conversion probability, prioritize sales efforts, and automate lead qualification using behavioral, firmographic, and engagement data from CRM platforms.

Expert guidance for building production-grade LLM applications with LangChain. Covers chain composition with LCEL, RAG pipelines, agent systems, LangGraph workflows, prompt engineering, and production deployment with LangSmith observability.

Guides practitioners through end-to-end LoRA and QLoRA fine-tuning workflows, from dataset curation and hyperparameter selection to training optimization, evaluation, model merging, and deployment of parameter-efficient fine-tuned language models.

Design and deploy predictive maintenance systems using edge computing, IoT sensor data, and machine learning models for anomaly detection and remaining useful life estimation in industrial environments.

Expert in TensorFlow and Keras — model building, training, TF Serving, TF Lite, TFX pipelines, and production deployment on Google Cloud.

Provides expert guidance on transformer neural network architectures, including attention mechanisms, positional encoding schemes, encoder-decoder design patterns, tokenization strategies, and context window optimization for building and understanding modern LLMs.

Design safe, effective tool-using AI agents with proper tool schemas, agent loop architecture, safety gates, and evaluation strategies for production LLM applications.

Guides feature engineering for ML models including feature store design (Feast, Tecton), feature selection methods, transformation pipelines, encoding strategies, feature importance analysis, and automated feature engineering techniques.

Design and implement MLOps platforms covering model serving, feature stores, CI/CD for ML, model monitoring, drift detection, A/B testing, and GPU resource management.

Expert in AI safety evaluation — adversarial testing, jailbreak prevention, prompt injection defense, bias detection, and safety benchmarking for LLMs and AI systems.

Design and optimize production-grade NLP pipelines covering text preprocessing, tokenization, NER, sentiment analysis, and transformer-based architectures using spaCy and HuggingFace.

Design comprehensive evaluation systems for LLMs and AI applications, covering automated metrics, human evaluation protocols, LLM-as-a-judge pipelines, and CI/CD-integrated regression testing.

Designs optimal text chunking strategies for Retrieval-Augmented Generation (RAG) systems, balancing chunk size, semantic coherence, retrieval precision, and generation quality across diverse document types.