Senior AI Engineer, AI Safety
Core
Architecting and developing fundamental elements of safety infrastructure to secure and align advanced AI systems, focusing on autonomous automation cycles for harm detection and content moderation.
Role type
Senior IC AI Safety Engineer (Agentic Systems)
Builds
Scalable automated research pipelines, safety models, and production guardrails for AI systems.
Domain
AI Safety, Autonomous Agents, Machine Learning
Deliverable
production ML models
Required skills
Agentic systems & automation, LLM orchestration, Rust, Python, PyTorch, End-to-end execution, Complex workflow design
Preferred skills
Trust & Safety background, Adversarial ML, Auto-research frameworks, AI safety benchmarking
Technologies
LLMs, PyTorch, Rust, Python, LangChain, AutoGPT, Semantic Kernel
Responsibilities
Architect agentic automation loops for safety evaluations and model testing; Develop specialized safety models for harm detection and run-time guard-railing; Build automated research frameworks using LLMs to discover vulnerabilities; Scale proof-of-concept safety interventions into production pipelines; Partner with researchers and platform engineers to bridge theory and practice.
