SambaNova is hiring a new graduate AI Performance Engineer for its AI Performance team. The team brings up and optimizes foundation models, including DeepSeek, Llama, Qwen, and GPT OSS, on SambaNova’s dataflow platform. It profiles and tunes models across compiler, runtime, and hardware layers to improve inference throughput and latency. In this role, you will bring up open-source models on the SambaNova stack, profile model execution, identify bottlenecks, and apply optimizations such as quantization, kernel fusion, and improved scheduling in collaboration with compiler, runtime, and hardware teams.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Entry Level