skills.rest
tcvdog
tcvdogCOMMUNITY
Explore all skills by this author →
GitHub

AI Engineer

Builds and deploys machine learning models into production systems with MLOps pipelines.

2|Updated May 21, 2026
Search Tags:#mlops#llm#rag#machine learning#PyTorch#tensorflow#model deployment
One-click install
npx skills add https://github.com/tcvdog/agency-agents-hermes --skill ai-engineer-tcvdog
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: AI Engineer
Source: https://github.com/tcvdog/agency-agents-hermes/tree/main/engineering/ai-engineer
Command: npx skills add https://github.com/tcvdog/agency-agents-hermes --skill ai-engineer-tcvdog

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Teams struggle to move machine learning models from experimentation to reliable production deployment while maintaining performance, fairness, and cost control. This Skill provides an expert AI/ML engineering persona that guides model development, deployment, and monitoring end to end. ## Core Features & Use Cases - Model Development Lifecycle: Covers data preparation, training, evaluation, and validation using TensorFlow, PyTorch, Scikit-learn, and Hugging Face. - Production Deployment & MLOps: Guides model serving with FastAPI, MLflow, and Kubeflow, including monitoring, drift detection, and automated retraining. - AI Ethics & Safety: Implements bias testing, fairness metrics, privacy-preserving techniques, and explainable AI practices. - Use Case: You need to deploy an LLM-powered recommendation feature. The Skill walks you through RAG implementation, vector database selection, API endpoint creation, and latency optimization to hit sub-100ms inference targets. ## Quick Start Ask the AI Engineer to design a production deployment plan for your machine learning model including monitoring and drift detection.

Frequently Asked Questions about AI Engineer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy a machine learning model to production?▼

Deploy a model by serializing and versioning it with MLflow, creating an API endpoint with FastAPI or Flask, and configuring load balancing with auto-scaling. Add monitoring for performance drift and set up automated retraining triggers.

What ML frameworks should I use for model development?▼

TensorFlow and PyTorch handle deep learning workloads, Scikit-learn covers classical ML, and Hugging Face Transformers supports LLM fine-tuning. Choose based on your model type, team expertise, and deployment target.

How do I implement a RAG system with vector databases?▼

Implement RAG by embedding documents into a vector database like Pinecone, Weaviate, Chroma, FAISS, or Qdrant, then retrieving relevant context at query time for the LLM. Combine with prompt engineering for grounded responses.

How do I detect bias in machine learning models?▼

Detect bias by testing model performance across demographic groups and computing fairness metrics during evaluation. Apply fairness-aware training techniques and document interpretability using explainable AI methods.

Why is my model inference latency too high in production?▼

High latency usually comes from unoptimized model size, synchronous processing bottlenecks, or insufficient scaling. Apply model compression, use batch or streaming patterns where appropriate, and target under 100ms for real-time APIs.

When should I use edge deployment instead of cloud inference?▼

Use edge deployment when privacy requirements demand on-device processing or when network latency makes cloud calls impractical. Hybrid strategies combine cloud training with edge inference for latency-sensitive applications.

Related Skills

Explore More Software Engineering Skills→
issdandavisissdandavis
6

scbe-training-pipeline

Merge and validate SFT training data sources for publishing.

Community
Advanced
ToXMonToXMon

domino-model-endpoints

Deploys and monitors model API endpoints on Domino Data Lab via REST and Grafana dashboards.

Community
Advanced
saitarrunsaitarrun
4

observability

Implement metrics, logs, and traces with SLO-driven alerting for production systems.

Community
Intermediate
frankxaifrankxai
2

AWS AI Services Expert

Coordinate Bedrock, SageMaker, and AWS AI services to automate enterprise AI workflows.

Community
Advanced