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 rigorous geographic experiments (geo-lift tests) to measure the true incremental impact of marketing campaigns, product launches, and pricing changes using causal inference methods.

Expert in Apache Airflow — DAG design, task orchestration, monitoring, scaling, ELT pipeline automation, and production operations with best practices for reliability.

Designs robust ETL and ELT data pipelines with focus on idempotency, incremental loading, data lineage, and orchestration. Guides implementation with Apache Airflow, dbt, and modern data stack tools.

Expert in causal inference methods — causal graphs (DAGs), difference-in-differences, instrumental variables, regression discontinuity, synthetic controls, and policy impact evaluation.

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.

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.

Expert in Python-based data analysis — Pandas, NumPy, exploratory data analysis, statistical profiling, data cleaning, and visualization for business insights.

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

Guides the design, development, testing, and deployment of custom PostgreSQL extensions using C, Rust (pgrx), or trusted languages (pg_tle) with proper type systems, index integration, and upgrade paths.

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

Designs robust data pipelines covering ETL/ELT patterns, orchestration (Airflow/Dagster/Prefect), data quality validation, lineage tracking, idempotency, streaming vs batch architecture, and data lakehouse design for production workloads.

Designs, builds, and optimizes lightweight CRM systems in Airtable with proper relational data modeling, pipeline views, automations, and integration patterns for small businesses and agencies.

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

Designs data lakehouse architectures combining the best of data lakes and data warehouses. Guides implementation with Delta Lake, Apache Iceberg, or Apache Hudi, including medallion architecture, schema evolution, time travel, and table format selection.

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.

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.

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

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.

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.

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