Research Engineer, AI Safety & Alignment
Core
Developing novel evaluation methodologies and metrics to assess the safety and alignment of large language models, conducting adversarial testing, and mitigating biases and harmful behaviors.
Role type
Research Engineer, AI Safety & Alignment
Builds
Production-facing safety solutions and evaluation frameworks for large language models
Domain
Artificial Intelligence, Machine Learning, AI Safety
Deliverable
production ML models
Required skills
PhD in Computer Science/Machine Learning, writing production code, GPU training and serving, data pipelines, transformers, reinforcement learning
Preferred skills
product experimentation, distributed model training, ML deployment orchestration, explainable AI, academic publications
Technologies
Kubernetes, Docker, cloud platforms
Responsibilities
Develop evaluation methodologies for LLM safety, research model alignment and interpretability techniques, conduct adversarial testing, analyze and mitigate model biases, collaborate on translating research to scalable solutions, contribute to academic community
Seniority
Senior, hands-on IC with research focus