AI Performance Engineer - New Grad
Core
Bring up new foundation models on the SambaNova platform and profile performance across compiler, runtime, and hardware layers to identify bottlenecks and propose optimizations.
Role type
New Grad AI Performance Engineer
Builds
Foundation models on the SambaNova platform
Domain
AI infrastructure / High-performance computing
Deliverable
production ML models
Required skills
Python, C++, PyTorch, TensorFlow, JAX, vLLM, TensorRT, SGLang, CUDA, Triton, algorithms, data structures, numerical computing
Preferred skills
LLM training or inference experience, quantization, graph optimization, kernel fusion, model partitioning, memory hierarchy, caching, scheduling, internship or research experience in ML systems, publications or open-source contributions
Technologies
SambaNova platform, PyTorch, TensorFlow, JAX, vLLM, TensorRT, SGLang, CUDA, Triton
Responsibilities
Profile model performance across compiler, runtime, and hardware layers; Identify bottlenecks and propose dataflow or scheduling optimizations; Apply quantization, scheduling, and memory optimization techniques; Benchmark inference throughput and latency; Collaborate with machine learning, compiler, runtime, and hardware teams
Seniority
New Grad
