Senior Ml Engineer

ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs.

Development / Engineeringdevelopmentengineering
by AgentVoltv1.0.0Published 1y ago1 install
Free to sign up · every skill included with AgentVolt Pro

Before & after

Same prompt, same agent — the only difference is the skill.

PromptSet up monitoring for model drift in production.
Beforegeneric AI agent
Model drift monitoring is important for maintaining model performance over time. You'll want to set up some kind of tracking for how your model's predictions compare to actual outcomes, and alert if there's significant degradation. You might use tools like MLflow or Evidently AI to help with this. You should probably define what drift means for your use case—whether it's prediction shift, feature shift, or performance degradation. You'd want to collect baseline metrics from when the model was trained and compare current performance to those baselines. It might help to set up automated alerts when performance drops below a threshold. You could also periodically retrain your model on fresh data. Would you like guidance on which monitoring tool to use, or help defining drift thresholds for your specific problem?
Afterwith Senior Ml Engineer
MODEL DRIFT MONITORING SETUP

DEFINE DRIFT TYPES
→ Data drift: Feature distributions changed (e.g., user demographics shift)
→ Prediction drift: Model output distribution drifts (e.g., predictions skewed to one class)
→ Performance drift: Accuracy drops vs. production baseline (e.g., precision drops below 85%)

BASELINE METRICS (from training)
→ Accuracy: 0.89 (Recorded: 2026-06-01)
→ Precision (class A): 0.91
→ Recall (class A): 0.87
→ Feature means + std (all 47 features logged)

MONITORING PIPELINE
→ Tool: Evidently AI (open source) or Arize (managed)
→ Cadence: Daily checks at 2am UTC
→ Sample: Latest 1,000 predictions + actuals
→ Metrics computed: KS test for distribution shift, current accuracy vs. baseline

ALERT THRESHOLDS
→ CRITICAL (page on-call): Accuracy drops >5% (below 0.84)
→ WARNING: Any feature drifts >3 std from baseline
→ INFO: Prediction distribution shift >10% (logged, not alerted)

RESPONSE PLAYBOOK
CRITICAL ALERT → Investigate root cause (feature drift? label corruption? concept drift?)
→ If fixable (bad feature): Hot-patch feature pipeline
→ If model issue: Trigger retraining on last 30 days data
→ If data issue: Quarantine predictions, rollback to previous model version

IMPLEMENTATION
→ Dashboard: Shows current metrics vs. baseline, drift score over time
→ Logging: All predictions logged to data warehouse for audit
→ Cost: ~200/month for monitoring service + retraining compute

About this skill


name: senior-ml-engineer description: Use when ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs.

Senior Ml Engineer

ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment, feature stores, drift monitoring, RAG systems, and cost optimization. Use when the user asks about deploying ML models to production, setting up MLOps infrastructure (MLflow, Kubeflow, Kubernetes, Docker), monitoring model performance or drift, building RAG pipelines, or integrating LLM APIs with retry logic and cost controls. Focused on production and operational concerns rather than model research or initial training.

What you get

  • Public GitHub repo (alirezarezvani/claude-skills)
  • the senior-ml-engineer skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.

Customize your output

  • Fork the repo and adapt the skill's instructions and references to your workflow.

Example output

Activates automatically when your request matches Senior Ml Engineer; chains with the other skills, agents, and commands in the collection.

Best for

Creators, builders, and teams using Claude Code.

SKILL.md preview

SKILL.md
---
name: senior-ml-engineer
description: Use this skill when deploying ML models to production, setting up MLOps infrastructure, monitoring model drift, building RAG pipelines, or integrating LLM APIs with cost controls.
version: 1.0.0
category: Development / Engineering
author: AgentVolt
license: proprietary
tags:
  - development
  - engineering
---

# Senior Ml Engineer

Covers productionizing machine learning models: deployment, feature stores, drift monitoring, RAG pipeline construction, and LLM integration with retry logic and cost controls, focused on operational concerns rather than research or training.

## When to use

… (sign up to view the full skill)
Sign up to view, copy, and install the full skill

More development skills

View all Development skills →