Applied AI Engineer - Multimodal Transformers
仕事内容
Design and develop multimodal transformer architectures that fuse camera, LiDAR, and radar into unified representations.
Advance cross-modal attention, token fusion strategies, and efficient multi-stream tokenization for robust sensor fusion.
Build scalable training pipelines for large-scale multimodal transformers across real-world datasets.
Explore self-supervised and contrastive pretraining objectives to learn transferable multimodal representations.
Optimize transformer models for real-time inference under latency and compute constraints while prioritizing safety.
Collaborate with cross-functional teams and contribute to cutting-edge research and scalable deployment.
Advance cross-modal attention, token fusion strategies, and efficient multi-stream tokenization for robust sensor fusion.
Build scalable training pipelines for large-scale multimodal transformers across real-world datasets.
Explore self-supervised and contrastive pretraining objectives to learn transferable multimodal representations.
Optimize transformer models for real-time inference under latency and compute constraints while prioritizing safety.
Collaborate with cross-functional teams and contribute to cutting-edge research and scalable deployment.
求人の全文を見る
業務内容、求める人物像、スキル、待遇 — 無料アカウントの作成で閲覧できます。
または
すでにアカウントをお持ちですか?
ログイン類似の求人
あなたに合いそうな他の職種。
勤務地Mountain View, United States