Senior AI Engineer, AI Safety

Sourced from nvidia.wd5.myworkdayjobs.com

NVIDIA's AI Safety Engineering team is hiring a Senior AI Engineer to scale methods for securing and aligning advanced AI systems. The role focuses on architecting agentic automation loops, building safety models for harm detection and guardrails, and pioneering automated research frameworks. You will partner with research and model development teams to turn safety research into scalable production systems.

• Architect, build, and deploy agentic automation loops for safety evaluations, red-teaming, model testing, and post-training
• Develop and train specialized safety models for harm detection, content moderation, and runtime guardrails
• Build automated research frameworks using LLMs and autonomous agents to discover vulnerabilities and generate safety datasets
• Engineer proof-of-concept safety interventions into robust, scalable production solutions
• Collaborate with researchers, platform engineers, and data scientists to bridge safety research and practical systems

• Bachelor's or Master's degree in Computer Science, Machine Learning, Software Engineering, or related field
• 8+ years of experience in ML engineering or software engineering
• Proven experience building complex automated workflows with LLMs, including multi-turn tool-calling, orchestration, and autonomous agent loops
• Deep proficiency in Rust or Python
• Experience with ML frameworks such as PyTorch
• Strong track record of end-to-end execution from research idea to production deployment

• Prior domain experience in Trust & Safety, cybersecurity, threat intelligence, adversarial machine learning, or content moderation
• Hands-on experience developing or deploying models for harm detection, content safety filtering, or runtime AI guardrails
• Contributions to projects using LLMs to automate coding, data synthesis, or scientific research
• Active contributions to public agent frameworks (LangChain, AutoGPT, Semantic Kernel) or AI safety benchmarking tools