AI Performance Engineer — Inference & Optimizations

SambaNova, Inc.; Austin (TX); On-site; USD 131,000 - 197,000; Full time

Benefits offered by this job

Health insurance

HSA

Dental

Vision

Employee Assistance Program

Headspace

Gympass+

One Medical

Job summary

SambaNova, Inc. is seeking a new‑grad AI Performance Engineer to bring up open‑source models on the SambaNova stack and improve their speed.

You will profile execution across compiler, runtime, and hardware layers, identify bottlenecks, and apply quantization, kernel fusion, and scheduling optimizations. You’ll collaborate with ML, compiler, runtime, and hardware teams to ship performance improvements in SambaNova products and contribute to state‑of‑the‑art inference performance.

Qualifications

• B.S. in CS, 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.

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 the machine learning, compiler, runtime, and hardware teams to ship performance improvements into SambaNova products.

Skills

Python

C++

Algorithms

Numerical computing

PyTorch

TensorFlow

JAX

vLLM

TensorRT

SGLang

CUDA

Triton

Quantization

Scheduling

Distributed systems

Education

B.S. in CS/EE

MS/PhD in CS/EE

Job description

SambaNova, Inc. is seeking a new‑grad AI Performance Engineer to bring up open‑source models on the SambaNova stack and improve their speed.

You will profile execution across compiler, runtime, and hardware layers, identify bottlenecks, and apply quantization, kernel fusion, and scheduling optimizations. You’ll collaborate with ML, compiler, runtime, and hardware teams to ship performance improvements in SambaNova products and contribute to state‑of‑the‑art inference performance.