Founding Lead Machine Learning Engineer
Cette offre est-elle pour vous ?
Créer mon CV Créez votre CV et découvrez votre pourcentage de correspondance avec ce poste — et avec tous les autres.
Suivez vos candidatures sur mobile L'application Whileresume, gratuite, sur iPhone et Android.
Le poste
Lead the core ML technical direction for a new global consumer AI product, shaping model selection, training strategy, and long-term architecture.
Design and build end-to-end training pipelines from data collection to evaluation and scalable inference.
Architect and adapt frontier models (LLaMA, Mistral, Qwen, Claude-compatible) and develop new approaches where needed.
Fine-tune models with state-of-the-art methods (LoRA/QLoRA, SFT, DPO, distillation) and optimize GPU-driven deployment.
Create robust data systems for high-quality synthetic and real-world training data; develop alignment, safety, and guardrails; build evaluation frameworks.
Own deployment decisions, explore new use cases, and push frontier techniques (retrieval augmentation, mixture of experts, multi-agent orchestration, multimodal models) to ship AI-powered experiences.
Design and build end-to-end training pipelines from data collection to evaluation and scalable inference.
Architect and adapt frontier models (LLaMA, Mistral, Qwen, Claude-compatible) and develop new approaches where needed.
Fine-tune models with state-of-the-art methods (LoRA/QLoRA, SFT, DPO, distillation) and optimize GPU-driven deployment.
Create robust data systems for high-quality synthetic and real-world training data; develop alignment, safety, and guardrails; build evaluation frameworks.
Own deployment decisions, explore new use cases, and push frontier techniques (retrieval augmentation, mixture of experts, multi-agent orchestration, multimodal models) to ship AI-powered experiences.
Voir l'offre en entier
Missions, profil recherché, compétences et avantages — en créant votre compte gratuitement.
ou
Déjà un compte ?
Se connecterCes offres pourraient vous intéresser
Aucune offre vraiment proche pour l'instant — voici les plus récentes.