Browse Skills

Designs end-to-end computer vision pipelines including model selection (CNN/ViT/YOLO), data augmentation, training strategies, transfer learning, and production deployment with ONNX/TensorRT optimization for cloud and edge.

Design rigorous, bias-minimized surveys — from research objective clarification and question writing to sampling strategy, skip logic, and analysis planning.

Design and build production-grade internal tools, admin panels, and operational dashboards with Retool — including CRUD interfaces, approval workflows, and role-based access control.

Design and implement digital twin systems that create virtual representations of physical assets using IoT sensor data, simulation models, and cloud platforms for predictive maintenance and operational optimization.

Master SQL window functions for advanced analytical queries including ranking, running aggregates, time-series analysis, and cohort calculations across PostgreSQL, Snowflake, and BigQuery.

Design and deploy edge computing systems for industrial energy monitoring, combining IIoT sensor networks with real-time analytics to deliver consumption transparency, anomaly detection, and ISO 50001-aligned energy management.

Expert guidance for creating compelling geospatial visualizations and spatial data analysis. Covers map design, PostGIS spatial queries, web mapping libraries (Mapbox, Deck.gl, Leaflet), data formats, and location intelligence.

Design and operate low-latency feature delivery systems for production ML, including feature store architecture, online/offline consistency, streaming pipelines, and serving infrastructure optimization.

Analyzes and optimizes Elasticsearch query performance, index mappings, and cluster configurations to achieve faster search latency and lower resource consumption.

Design and implement structured deep learning training workflows using PyTorch Lightning, covering LightningModule architecture, distributed training strategies, experiment tracking, checkpoint management, and production model deployment.

Guides ML practitioners in designing rigorous experiment tracking workflows using MLflow, Weights & Biases, and related tools, covering hyperparameter optimization, reproducibility, model registry, and team collaboration patterns.

Evaluates machine learning models with rigorous methodology and statistical analysis. Covers metrics selection, cross-validation strategies, bias detection, A/B testing, confusion matrices, ROC/AUC analysis, and comprehensive evaluation reporting.

Designs effective prompts and prompt chains for LLM applications. Covers chain-of-thought reasoning, few-shot learning, system prompt architecture, output formatting, prompt evaluation, and reusable template design.