New Grad AI Performance Engineer

SambaNova, Inc.; San Jose (CA); On-site; USD 131,000 - 197,000; Full time

Benefits offered by this job

Healthcare coverage

Headspace membership

Gympass+ membership

One Medical membership

Employee Assistance Program

Flexible Spending Account options

Job summary

SambaNova is seeking a new graduate AI Performance Engineer to bring up open source models on the SambaNova stack and optimize them for faster inference. You will profile model execution, identify bottlenecks, and apply optimizations such as quantization, kernel fusion, and scheduling improvements across the compiler, runtime, and hardware teams for single-node and distributed systems.

You'll work with ML researchers, compilers, and hardware engineers to ship performance improvements into

Qualifications

• Bachelor’s degree in CS, EE, 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.

Responsibilities

• 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 ML, compiler, runtime, and hardware teams to ship performance improvements into SambaNova products.

Skills

Python

C++

Algorithms

Data structures

Numerical computing

Education

B.S. in Computer Science, Electrical Engineering, or related field

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

Tools

PyTorch

TensorFlow

JAX

vLLM

TensorRT

SGLang

CUDA

Triton

Job description

SambaNova is seeking a new graduate AI Performance Engineer to bring up open source models on the SambaNova stack and optimize them for faster inference. You will profile model execution, identify bottlenecks, and apply optimizations such as quantization, kernel fusion, and scheduling improvements across the compiler, runtime, and hardware teams for single-node and distributed systems.

You'll work with ML researchers, compilers, and hardware engineers to ship performance improvements into