Software Engineer - GPU Networking & Distributed Systems
Toronto, ON +1Baseten
Baseten needs deep experience with high-performance networking such as InfiniBand and RoCE v2, and fluency in C++ or Python. Candidates should understand NVIDIA GPU memory architecture and be comfortable debugging low-level systems.
InfiniBand, RoCE, NCCL, NVSHMEM, NVLink, TensorRT-LLM
Software Engineer - Model Performance Systems
Toronto, ON +1Baseten
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
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
Software Engineer - Infrastructure
Toronto, ON +1Baseten
Baseten needs candidates with a Bachelor's degree or higher in Computer Science or a related field, working coding skills, and a working knowledge of Kubernetes and containers. Basic ML concepts, distributed systems familiarity and monitoring tool experience are also asked for.
Kubernetes, Go, Python
Software Engineer - Dedicated Inference
Toronto, ON +1Baseten
Candidates need a bachelor's degree or higher in computer science or a related field and proficient coding skills in one or more languages, with Python, Go or JavaScript a plus. Familiarity with web applications and databases, good product judgment for developer tools, and strong collaboration skills are also expected.
React, Kubernetes