Browse Skills

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 optimal database indexing strategies by analyzing query patterns, understanding index internals, and balancing read performance against write overhead for PostgreSQL, MySQL, and other relational databases.

Designs and implements time series forecasting solutions — from data preprocessing and stationarity testing through model selection (ARIMA, Prophet, LSTM, Transformer-based), evaluation with proper temporal cross-validation (MAPE, RMSE, MASE), to production deployment with ensemble approaches and drift monitoring.

Designs and implements Monte Carlo simulations for quantitative analysis, covering probability distributions, variance reduction techniques, financial modeling (VaR, options pricing), convergence analysis, sensitivity analysis, and production-quality Python/R implementation patterns.

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.

Expert guidance on real-time stream processing architectures using Apache Kafka, Flink, and Spark Streaming, covering windowing strategies, exactly-once semantics, CEP, and operational best practices.

Designs normalized event tracking schemas for product analytics, defining event taxonomies, property standards, and validation rules to ensure consistent data collection across teams.

Design and build production-grade real-time data pipelines using Apache Kafka, Flink, Spark Streaming, and CDC patterns with exactly-once semantics and operational observability.

Designs unified customer profiles using Segment, RudderStack, or custom CDP solutions with identity resolution, event streaming, audience segmentation, and privacy-compliant data governance.

Builds and evaluates demand forecasting systems using statistical time series methods and machine learning, covering decomposition, model selection, accuracy measurement, and translation to inventory and planning decisions.

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.

Designs dimensional data warehouse schemas using Kimball, Inmon, or Data Vault methodologies. Guides star/snowflake schema design, slowly changing dimensions, ETL/ELT patterns, and cloud warehouse optimization for Snowflake, BigQuery, and Redshift.

Maps end-to-end data lineage from source systems through transformations to downstream consumers, enabling impact analysis, debugging data quality issues, and ensuring regulatory compliance.

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.

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.

Designs real-time analytics systems using stream processing frameworks like Kafka Streams, Apache Flink, and Spark Streaming. Covers event-time processing, windowing strategies, exactly-once semantics, and low-latency dashboard architectures.

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.

Guides analytics engineering best practices using dbt, SQL modeling patterns, semantic layers, metrics definitions, and testing strategies. Helps design maintainable, well-documented analytics workflows from raw data to business-ready datasets.

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

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

Guide practitioners through selecting, designing, and interpreting statistical hypothesis tests with proper assumptions checking, sample size calculations, and actionable conclusions.

Guide systematic exploratory data analysis workflows — from initial profiling through distribution analysis, correlation discovery, and hypothesis generation — using statistical rigor and effective visualization.