Browse Skills

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

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.

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.

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

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.

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 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 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.

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.

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.

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.

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 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.

Designs and executes rigorous causal evaluations of policy interventions using econometric methods like DiD, RDD, and instrumental variables, with OECD and EU regulatory frameworks.

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.

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

Prepare research outputs for public sharing and long-term preservation with FAIR-compliant data packaging, reproducible environments, proper licensing, and repository publication strategies.

Guides you through designing effective, insight-driven dashboards with proper KPI selection, visual encoding, and data storytelling — applying Tufte and Few principles to avoid common anti-patterns.

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

Expert analytics engineering skill for dbt Core/Cloud — guides you through SQL-based data modeling with staging/intermediate/mart layers, dimensional modeling (Kimball methodology), incremental models, SCD Type 2 snapshots, comprehensive testing strategies, Jinja macros, dbt packages, and warehouse-specific optimization for Snowflake, BigQuery, and Redshift.

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