AI Performance Engineer - New Grad (Model Tuning)

SambaNova Systems; San Jose (CA); Sur place; USD 131 000 - 197 000; Plein temps

Avantages offerts par ce poste

Health Insurance

HSA (Health Savings Account)

Dental

Vision

Disability Insurance

Life Insurance

Headspace

Gympass+

One Medical

Employee Assistance Program

Résumé du poste

SambaNova Systems is seeking a new graduate AI Performance Engineer to bring up open source models on our stack and optimize their performance. You will profile execution, identify bottlenecks, and apply quantization, kernel fusion, and scheduling improvements in collaboration with compiler, runtime, and hardware teams.

The role focuses on single-node and distributed systems, leveraging CUDA/Triton, PyTorch, and related frameworks to accelerate model inference.

Qualifications

• B.S. in Computer Science, Electrical Engineering, or related field.
• Strong programming skills in Python or C++.
• Understanding of algorithms, data structures, and numerical computing.
• Experience with PyTorch, TensorFlow, or JAX.
• Experience with inference frameworks such as vLLM, TensorRT, or SGLang.
• GPU programming experience with CUDA or Triton.

Responsabilités

• Bring up new foundation models on the SambaNova platform using our software stack.
• Profile model performance across the compiler, runtime, and hardware layers.
• Identify bottlenecks and propose dataflow or scheduling optimizations for single-node and distributed systems.
• Apply techniques from recent research in quantization, scheduling, and memory optimization.
• Benchmark throughput and latency and track performance changes across releases.
• Work with the machine learning, compiler, runtime, and hardware teams to ship performance improvements into SambaNova products.

Connaissances

Python

C++

PyTorch

TensorFlow

JAX

vLLM

TensorRT

SGLang

CUDA

Triton

Formation

Bachelor of Science in Computer Science, Electrical Engineering, or related field

M.S. or Ph.D. in Computer Science, Electrical Engineering, or related field

Description du poste

SambaNova Systems is seeking a new graduate AI Performance Engineer to bring up open source models on our stack and optimize their performance. You will profile execution, identify bottlenecks, and apply quantization, kernel fusion, and scheduling improvements in collaboration with compiler, runtime, and hardware teams.

The role focuses on single-node and distributed systems, leveraging CUDA/Triton, PyTorch, and related frameworks to accelerate model inference.