Research Engineer, Model Inference & Serving - Paris

Join H, a company dedicated to pushing the boundaries of superintelligence with agentic AI. As a Research Engineer in Model Inference & Serving, you will build and operate the inference stack that serves H's multimodal agentic models, improve latency, throughput, and cost of model serving, and collaborate with cross-functional teams to integrate inference into agentic AI products. You should have a strong software engineering background, experience with deep learning frameworks, and a passion for inference and AI. The position is hybrid, based in Paris or London, and offers a competitive salary and opportunities for professional growth.

• Construire et exploiter la pile d'inférence qui sert les modèles multimodaux agentiques de H.
• Améliorer la latence, le débit et le coût de la mise en service des modèles à travers la pile.
• Rechercher et mettre en œuvre des techniques d'inférence adaptées aux charges de travail des agents.