Staff Software Engineer, ML Acceleration

About the Role:

The ML Training Acceleration team is dedicated to increasing Stack AV's product development velocity by accelerating machine learning iterations. Our core mission is to deliver a training system that is reliable, scalable, user-friendly and observable. This involves profiling, optimizing, and fine-tuning our ML models, as well as evangelizing best practices and frameworks among Machine Learning Engineers (MLEs) across the company.

Responsibilities: 

• Analyze ML models to identify and resolve performance bottlenecks.
• Incorporate OSS tools to enable ML engineers self-sufficiently profile and optimize models.
• Deliver solutions to streamline model deployment across various hardware platforms.
• Collaborate with ML researchers to balance model accuracy and speed.
• Implement optimizations using CUDA, Triton, and custom kernels.
• Promote Engineering Excellence: Maintain a high bar for engineering excellence in their own work but also set a culture of engineering excellence within the team.

Qualifications: 

• Education: Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field
• Experience: 5+ years of experience (including experience with GPU programming and optimization)
• Technical Skills:
  • Strong programming skills in C++ and Python
  • Proven experience in GPU programming and optimization
  • Familiarity with deep learning frameworks, especially PyTorch
  • CUDA programming
  • Triton language for GPU kernels
  • PyTorch optimization techniques
  • TensorRT implementation
  • ONNX model conversion and deployment
  • Custom GPU kernel development
  • Deep understanding of GPU architectures and performance optimization
• Problem-Solving: Strong analytical and problem-solving skills
• Communication: Excellent verbal and written communication skills, with the ability to convey complex technical concepts to non-technical stakeholders
• Autonomous vehicles (AV) experience is a bonus