Senior Research Scientist - Multimodal Agents
¿Es esta oferta para usted?
Crear mi CV Cree su CV y descubra su porcentaje de coincidencia con este puesto — y con todos los demás.
Sigue tus candidaturas desde el móvil La app gratuita de Whileresume, en iPhone y Android.
El puesto
You will lead the research and engineering of multimodal agent systems, focusing on planning, tool use, memory, and retrieval to solve real design, vision, and language tasks.
Scale post-training and reinforcement learning across distributed PyTorch pipelines, ensuring efficient, reproducible training of large models and MoE architectures.
Design and implement reward models and learning loops (RLHF/RLAIF, preference modeling, DPO/IPO-style objectives, offline/online RL, curriculum learning) for multi-step reasoning.
Create simulation environments and evaluation suites to surface failure modes (planning errors, tool use brittleness, hallucination, unsafe actions) and turn them into measurable targets.
Lead rigorous evaluation: offline suites, online experiments, and data-backed conclusions; collaborate with product, safety, and platform teams to ship reliable features.
Mentor teammates, present results, and contribute to the research community while upholding high standards of reproducibility and safety.
Scale post-training and reinforcement learning across distributed PyTorch pipelines, ensuring efficient, reproducible training of large models and MoE architectures.
Design and implement reward models and learning loops (RLHF/RLAIF, preference modeling, DPO/IPO-style objectives, offline/online RL, curriculum learning) for multi-step reasoning.
Create simulation environments and evaluation suites to surface failure modes (planning errors, tool use brittleness, hallucination, unsafe actions) and turn them into measurable targets.
Lead rigorous evaluation: offline suites, online experiments, and data-backed conclusions; collaborate with product, safety, and platform teams to ship reliable features.
Mentor teammates, present results, and contribute to the research community while upholding high standards of reproducibility and safety.
Ver la oferta completa
Funciones, perfil, competencias y ventajas — crea tu cuenta gratis.
o
¿Ya tiene una cuenta?
Iniciar sesiónEstas ofertas podrían interesarte
Ninguna oferta realmente parecida por ahora — estas son las más recientes.