Browse Skills

Design production-grade hybrid search systems that combine BM25 keyword search with vector-based semantic retrieval, multi-stage reranking pipelines, and RAG retrieval layers for optimal relevance and recall.

Guides decisions on when and how to fine-tune large language models, covering LoRA/QLoRA, dataset curation, RLHF/DPO alignment, evaluation strategies, and cost-performance tradeoffs for production deployments.

Guides teams through MongoDB Atlas production deployments — cluster architecture, performance optimization, Atlas Search, security hardening, backup strategies, and cost management for cloud-native document database workloads.

Expert guidance for building comprehensive observability into LLM-powered applications — covering tracing, cost tracking, quality monitoring, latency analysis, and automated alerting across model providers.

Expert architect for designing multi-step prompt chains and orchestration patterns — from task decomposition and chain-of-thought sequencing to intermediate verification gates, context window management, error recovery strategies, and production-grade prompt pipeline design for complex LLM workflows.

Guide the end-to-end curation of high-quality datasets for machine learning. Covers data collection strategies, cleaning pipelines, annotation workflows, bias auditing, deduplication, and dataset documentation following data-centric AI principles.

Designs and implements sophisticated Airtable automations, scripting extensions, and integration workflows that transform manual business processes into reliable, scalable automated systems.

Design synthetic data generation pipelines that produce privacy-preserving, statistically faithful datasets for ML training, testing, and data sharing using GANs, copulas, and differential privacy.

Designs production-grade Retrieval-Augmented Generation pipelines including chunking strategies, embedding model selection, vector database architecture, hybrid search, reranking, and hallucination reduction techniques.

Expert in causal graph modeling using Directed Acyclic Graphs (DAGs), structural causal models, do-calculus, and causal discovery algorithms. Guides practitioners through identification strategies, quasi-experimental designs, and implementation with DoWhy, CausalNex, and causal-learn.

Builds structured competitive intelligence analyses including competitor profiling, feature parity matrices, win/loss patterns, pricing intelligence, and sales battlecards using proven CI frameworks and market research methodologies.

Performance tuning for Pinecone, Weaviate, Qdrant, and pgvector including index selection, embedding dimensionality, chunking strategies, and hybrid search optimization for RAG systems.

Expert in Google BigQuery — SQL analytics at scale, partitioning and clustering strategies, BigQuery ML, materialized views, Dataform pipelines, cost optimization, and data governance.

Design data activation pipelines that sync analytical data from cloud data warehouses back into operational SaaS tools like CRMs, marketing platforms, and support systems.

Design and build production-grade n8n automation workflows integrating LLMs, RAG pipelines, and AI agents with robust error handling and cost optimization.

Guides the end-to-end deployment of TensorFlow Lite models on mobile and edge devices — from model conversion and quantization to on-device inference optimization, hardware delegate selection, and production monitoring. Ensures models meet latency, size, and accuracy constraints for resource-constrained environments.

Build, evaluate, and deploy machine learning models directly in Google BigQuery using SQL, from classification and regression to time-series forecasting and recommendations.

Design, implement, and operate real-time event streaming systems using Redis Streams. Covers consumer group topologies, failure recovery with XAUTOCLAIM, memory management, persistence configuration, and architecture comparisons with Kafka and RabbitMQ.

Design BI architectures with semantic layers, dimensional models, self-service analytics, KPI frameworks, and modern data stack patterns using dbt, Looker, Metabase, and Tableau.

Conduct environmental lifecycle assessments (LCA) of products following ISO 14040/14044, covering goal definition, inventory analysis, impact assessment, and improvement recommendations for sustainable product design.

Designs comprehensive data labeling strategies including annotation pipeline architecture, inter-annotator agreement measurement, active learning loops, label quality control, crowdsourcing management, few-shot labeling, and weak supervision techniques.

Design and implement automated data quality validation pipelines using Great Expectations, with expectation suite design, threshold calibration, and integration into dbt, Airflow, and Spark workflows.

Optimize BigQuery deployments for maximum performance and minimum cost through partitioning, clustering, query tuning, and systematic cost control strategies.

Design and deploy Statistical Process Control systems with proper control chart selection, rational subgrouping, process capability analysis, and automated monitoring to detect and reduce process variation in manufacturing and service operations.