Staff Software Engineer, Deep Learning Acceleration for AVs

Aurora; San Francisco (CA); Hybrid; USD 189,000 - 274,000; Full time

Benefits offered by this job

Annual bonus

Equity compensation

Hybrid work environment

Job summary

Aurora is seeking a Staff Software Engineer focused on Deep Learning Acceleration to improve the performance of DL networks in our Autonomous Vehicle systems. You will analyze bottlenecks, optimize latency, and collaborate with engineers and researchers to deliver efficient, scalable solutions for on-vehicle and data-center training workloads.

You will work in a fast-paced, cross-functional environment, applying profiling techniques and roofline analysis while leveraging frameworks like PyTorch

Qualifications

• BS, MS, or PhD in Computer Science or a related field.
• Strong programming skills in CUDA, C++ and Python.
• Extensive experience in high-performance computing and parallel programming; optimize workloads to reduce GPU memory usage, latency, or maximize throughput.

Responsibilities

• Conduct performance analysis and optimization of Deep Learning networks running on the Autonomous Vehicle (AV).
• Optimize software architecture, system performance, and latency for deep learning applications.
• Deploy deep learning models on the AV and training on large-scale data centers.
• Troubleshoot performance issues using profiling and roofline model techniques.
• Collaborate with cross-functional teams to enhance the efficiency of self-driving technology.

Skills

CUDA

C++

Python

GPU optimization

Nsight

PyTorch

TensorFlow

Transformer models

Linux

Performance analysis

Roofline model

Deep learning

Education

Bachelor/Master/PhD in Computer Science or related field

Tools

NVIDIA Nsight Systems

NVIDIA Nsight Compute

TensorRT

OpenAI Triton

Mojo

Job description

Aurora is seeking a Staff Software Engineer focused on Deep Learning Acceleration to improve the performance of DL networks in our Autonomous Vehicle systems. You will analyze bottlenecks, optimize latency, and collaborate with engineers and researchers to deliver efficient, scalable solutions for on-vehicle and data-center training workloads.

You will work in a fast-paced, cross-functional environment, applying profiling techniques and roofline analysis while leveraging frameworks like PyTorch