Skills › AI Safety & Ethics

AI Safety Engineering

Implement guardrails, red-team prompts, and build safer AI applications.

0%
Confidence · no data yet
Sign in to track

After this skill you can…

  • Implement input and output guardrails
  • Red-team a deployed LLM application
  • Use Llama Guard or NeMo Guardrails

Prerequisites

Watch (10 videos)

AWS AI Practitioner Practice Exam #4 — Fine-Tuning, Bias, Guardrails & Governance
How To Center · beginner
→ Design AI systems with safety in mind→ Develop governance policies for AI
Auditable AI Tools: Scalable Governance for Next-Gen AI Systems
QuickTech Daily · beginner
→ Design safe AI systems→ Conduct AI audits→ Develop explainable AI models
Claude has a serious privacy problem
Edward Sturm · intermediate
→ Design and implement AI systems with privacy and security in mind→ Conduct risk assessments for AI-powered applications
Prompt Injection Explained: How AI Agents Get Tricked!
GenAI Geek · intermediate
→ Implement safety controls→ Test AI systems for security risks
Building confidence in AI: Operationalizing orchestration in regulated enterprises
UiPath · intermediate
→ Design safe AI systems→ Implement AI governance→ Ensure AI compliance
AI went rogue in real life...
Matthew Berman · beginner hands-on
→ Design secure AI systems→ Implement containment protocols→ Develop strategies for mitigating AI security risks
Why Open Source AI is Gaining Traction
The Information · advanced
→ Identify potential safety risks in AI systems→ Develop strategies for mitigating risks
Anthropic warns About This AI could escape control!
PlivoAI · beginner
→ Design AI safety systems→ Develop AI risk assessment frameworks→ Implement AI safety protocols
VSL International | Build a stronger safety culture through leadership | Bouygues Construction
Bouygues Construction · intermediate hands-on
→ Develop a safety leadership program→ Implement safety protocols→ Conduct risk assessments
ARC-AGI-3 Explained by the Team That's Winning It
Machine Learning Street Talk · advanced
→ Design safe AI systems→ Implement safety protocols in AI development

Read (10 articles)

📄
The GPT-5 Paradox: Genius in Thought, Gaps in Safety
Dev.to · Ayush kumar · 2025-08-14
📄
A small number of samples can poison LLMs of any size
Dev.to · Aman Shekhar · 2025-10-10
📄
Why Your AI Needs Both Intuition and Rules
Dev.to · AbdulGoniyy Adeleke Dare · 2025-12-30
📄
Llama Guard: What It Actually Does (And Doesn't Do)
Dev.to · Joshua Gracie · 2026-01-24