Technical Program Manager, Model Performance
Toronto, ON +1HybrideTemps plein
Baseten
Candidates need deep technical program management experience on complex programs, and experience with model performance or inference optimization. They should be comfortable building programs from ambiguity and influencing people without authority.
vLLM, TensorRT-LLM, SGLang, NVIDIA Dynamo
Software Engineer - Model Performance Systems
Toronto, ON +1HybrideTemps plein
Baseten
Candidates need Python skills, interest in GPU and networking systems, and an automation mindset. Strong communication, the ability to work with vague requirements and mentoring experience are also expected. C++ is a plus.
PyTorch Profiler, NVIDIA Nsight Systems, py-spy, GitHub Codespaces, InferenceMAX, genai-bench