Suggestions
Profils classés par recoupement avec les compétences et outils de ce poste — utile si vous recrutez une équipe ou comparez des profils.
D’autres annonces partageant compétences ou outils — utile pour des stacks comparables ou des options de repli.
·
Calling frontier APIs with retries, cost controls, prompt versioning, and safety filters.
Training and inference with PyTorch: reproducible experiments, checkpointing, and deployment-minded exports.
Intitulé
Ingénieur LLM freelance — mission RAG
Cohere
Cohere builds enterprise-grade language models and APIs used globally from our Toronto headquarters.Join as a Senior LLM Engineer to ship RAG, embeddings, and fine-tuning workflows for regulated customers.What you will doShip production LLM and retrieval systems with offline evals, monitoring, and…
Avantages · GPU access, equity, Toronto waterfront office.
Voir l’offre
LightOn
LightOn déploie des LLM souverains et des systèmes RAG enterprise pour des grands comptes européens depuis Paris.Ingénieur LLM RAG (hybride Paris 2e) : retrieval hybride, fine-tuning, évaluation qualité et mise en production sur modèles LightOn.À propos de LightOnScale-up française spécialisée…
Avantages · BSPCE, remote partiel, modèles souverains.
Voir l’offre
Tencent
Tencent operates WeChat, games, and cloud services — one of Asia's largest AI labs with a flagship office in Wan Chai, Hong Kong.Senior LLM Engineer (hybrid Hong Kong): Cantonese/Mandarin NLP, RAG assistants, and multimodal features for WeChat ecosystem products.About TencentHong Kong tower hosts…
Avantages · Hybrid Wan Chai, annual bonus, MPF.
Voir l’offre
DeepMind
DeepMind builds frontier AI for science and products used by Google and partners worldwide. Our London teams work on large-scale training, alignment, and safe deployment of language and multimodal systems.We are hiring a Staff LLM Engineer (hybrid, London) to lead retrieval-augmented and agentic…
Avantages · Private medical, pension, learning budget, hybrid 3/2.
Voir l’offre
Helio Foundry
Helio Foundry — Build and operate large-scale PyTorch fine-tuning for domain-specific LLMs: FSDP/DeepSpeed-style runs, LoRA/QLoRA recipes, data mixing, and eval gates before merge to production serving.Remote EU; overlap CET ±2h.
Avantages · A100/H100 cloud budget; conference pass.
Voir l’offre