Senior Staff Software Engineer – ML Acceleration Lead

About the Role:  

The training and deployment team, part of the ML Platform org at Stack AV, is responsible for the platform that helps the AI team to build models, optimize, test, and deploy them on the autonomous vehicles. We are seeking an experienced, visionary, and hands-on technical lead for our ML acceleration team. This role will be responsible for designing the architecture and leading a team to automate the optimization and deployment on complex ML models (including transformer-based models such as VLM models) for all the next-gen AI Autonomous Vehicle applications in the company. The ideal candidate will have a deep understanding of GPUs and optimization, excellent leadership skills, and the ability to drive technical excellence.

Responsibilities:

• Analyze and profile ML models to identify performance bottlenecks.
• Use OSS tooling to enhance our platform to enable ML engineers to profile models and optimize them (e.g., through quantization).
• Automate the process of exporting the model to optimized format (e.g., TensorRT) and deploying them.
• Implement optimizations using CUDA, Triton, and custom kernels.
• Collaborate with ML researchers to balance model accuracy and speed.
• Lead efforts within the team as well as cross-team projects related to model optimization and deployment.
• Collaborate with cross-functional teams to understand data requirements and design appropriate solutions.
• Stay updated with the latest technologies and trends in ML inference and ML accelerators.
• Identify and resolve performance bottlenecks in models.
• Set a culture of engineering excellence within the team and work closely with the management and customer teams to balance between speed of delivery and quality of engineering artifacts.

Qualifications:

• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
• 5+ years of experience in GPU programming and optimization.
• 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
• Proven ability to lead and mentor a team, manage projects, and drive technical initiatives.
• Strong analytical and problem-solving skills.
• Excellent verbal and written communication skills, with the ability to convey complex technical concepts to non-technical stakeholders. #LI-AW1