Senior Ml Engineer

This covers the production ML engineering stack you'd actually need: deployment workflows with Docker and serving options like Triton or Ray Serve, MLOps pipelines with feature stores and experiment tracking, and RAG system implementation with vector database comparisons. The monitoring section gives you drift detection code and alert thresholds that aren't just theoretical. What's useful here is the decision matrices, like when to use which chunking strategy or which LLM provider based on cost per token. It assumes you already know ML fundamentals and need the infrastructure patterns to ship models rather than just train them. The canary deployment workflow and retraining triggers are especially practical if you're moving from notebooks to production.

skills.sh installs: 182
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add borghei/claude-skills --skill senior-ml-engineer --agent claude-code

Installs into .claude/skills of the current project.

Files

Senior ML Engineer

Production ML engineering patterns for model deployment, MLOps infrastructure, and LLM integration.

Core Capabilities

Model deployment — export to ONNX/TorchScript/SavedModel, containerize, canary rollout, and serve via FastAPI, Triton, TF Serving, TorchServe, or Ray Serve with p95<100ms / error<0.1% gates.
MLOps pipelines — feature stores (Feast/Tecton), experiment tracking (MLflow/W&B), model registry, A/B testing, and drift-triggered retraining.
LLM integration — provider abstraction, retry/fallback with exponential backoff, token counting, response caching, cost tracking, and Pydantic output validation.
RAG systems — vector database selection, chunking strategies, ingestion, retrieval, and reranking.
Model monitoring — latency/error tracking, input drift detection (KS test, PSI), prediction-shift alerts, and automated retraining triggers.