Software Engineer - Inference Platform
Toronto, ON +1Baseten
3+ ansCandidates need 3+ years building distributed systems or large-scale backend APIs, with experience in low-latency services, observability and performance profiling. Kubernetes, GPU workloads and LLM inference experience are assets, but prior ML experience is not required.
Kubernetes, GPU, vLLM, SGLang, TensorRT-LLM, NVIDIA Dynamo
Software Engineer - Inference Performance
Toronto, ON +1Baseten
Candidates need a bachelor's, master's or PhD in a technical field, experience with Python or C++, and familiarity with LLM optimization and ML libraries such as PyTorch or TensorRT. They also need a deep understanding of GPU architecture and demonstrated interest in LLMs.
PyTorch, TensorRT, TensorRT-LLM, vLLM, SGLang, CUDA
Software Engineer - GPU Kernels
Toronto, ON +1Baseten
Candidates need a strong understanding of GPU architecture and memory hierarchy, proficiency in C++ and GPU profiling tools, and knowledge of the CUDA C++ API, numerical precision and modern GPU features. Experience with Transformer models, Flash Attention, Cutlass, Triton or GEMM tuning is a plus.
CUDA, PTX, Nsight Systems, Nsight Compute, Torch Profiler, Cutlass