Engineering Manager (Inference Performance)

Join Baseten, a remote-first company focused on making AI workloads run faster and more efficiently on GPUs. As an Engineering Manager, you will lead a team of inference performance engineers, manage the technical roadmap, and drive the productionization of inference techniques. You will also have the opportunity to shape the team's structure as it grows and set high standards for engineering quality.

• Gérer et développer une équipe d'ingénieurs en performance d'inférence, en fournissant un leadership technique et en favorisant leur croissance professionnelle.
• Définir la feuille de route technique et l'exécution des travaux de performance d'exécution, en équilibrant les besoins des clients et les investissements à long terme.
• Collaborer avec d'autres équipes pour établir des priorités, coordonner les lancements et expédier les gains.

• Experience managing engineers, including hiring, mentoring, giving feedback and running performance reviews
• A track record of driving roadmaps and shipping complex technical projects with a team
• Strong technical depth in GPU workloads, with a solid understanding of GPU architecture and performance tradeoffs
• Clear written and verbal communication, including the ability to align stakeholders across teams
• Familiarity with ML libraries such as PyTorch, TensorRT or TensorRT-LLM
• Bachelor's, Master's, or Ph.D. degree in Computer Science, Engineering, Mathematics, or a related field
• Experience leading or closely supporting GPU optimization teams in training, inference or recommendation systems
• Familiarity with inference engines such as vLLM, SGLang or TensorRT-LLM
• Experience with LLM optimization techniques (e.g., quantization, speculative decoding, continuous batching) in production
• Experience with GPU kernels (CUDA, Triton, CUTLASS, or similar)
• Experience scaling a team through rapid growth at a startup
• A background as a hands-on performance or systems engineer before moving into management