- Santa Clara, California, United States
- Full-time · Senior
- $184K–$429K per year
- 8+ years
Compensation
The expected base salary ranges for this position are: 183,750 USD – 351,000 USD for Level 4; and 225,000 USD – 429,000 USD for Level 5.
Responsibilities
- Apply fundamental and applied safety research to develop, train, fine-tune, and deploy large language architectures supporting multimodal agentic reasoning systems and guardrails encompassing text, audio, image, video, and tool usage.
- Advance post-training and alignment methods including instruction tuning, preference optimization, and RLHF/RLVR/MOPD to improve safety of multimodal agents for complex use cases.
- Research and advance the latest trends in AI safety as applied to pre-/mid-/post-training, guardrails, and steering techniques.
- Lead the collection, development, and benchmarking of multimodal safety datasets, ensuring high-quality evaluation of model accuracy, safety, and task completion success.
Requirements
- Master’s degree (or equivalent experience) or PhD in Computer Science, AI, or Applied Math
- Nice to have: publications in top-tier AI and machine learning venues such as NeurIPS, ICML, ICLR, FAccT, or CVPR
- Nice to have: deep reinforcement learning techniques to train multimodal agents in complex simulation
- Nice to have: addressing safety and legal and regulatory compliance in multimodal, multilingual, or multi-turn systems
- Nice to have: dynamic and multi-turn alignment benchmarks