AI Infrastructure Engineer (Serving Platform)

Join our ML Infrastructure team as an AI Infrastructure Engineer. You will design and build platforms for scalable and efficient serving of LLMs, supporting both research and production systems. The ideal candidate has strong ML fundamentals and deep expertise in backend system design. You will collaborate with researchers and engineers, conduct architecture and design reviews, develop monitoring solutions, and lead projects end-to-end. Enjoy comprehensive health coverage, personal and career growth opportunities, a supportive community, and parental support.

• Concevoir et construire des plateformes pour le service évolutif, fiable et efficace des LLMs.
• Collaborer avec des chercheurs et des ingénieurs pour intégrer et optimiser les modèles pour les cas d'utilisation de production et de recherche.
• Diriger des projets de bout en bout, de la collecte des exigences à la mise en œuvre, dans un environnement interfonctionnel.
• Experience with LLM capabilities and concepts such as reasoning, tool calling, prompt templates, etc
• Proven ability to solve complex problems and work independently in fast-moving environments
• Familiarity with cloud infrastructure (AWS, GCP) and infrastructure as code (e.g., Terraform)
• Experience with containers and orchestration tools (e.g., Docker, Kubernetes)
• Strong programming skills in one or more languages (e.g., Python, Go, Rust, C++)
• Experience with LLM serving and routing fundamentals (e.g. rate limiting, token streaming, load balancing, budgets, etc.)
• 4+ years of experience building large-scale, high-performance backend systems
• Experience with modern LLM serving frameworks such as vLLM, SGLang, TensorRT-LLM, or text-generation-inference