Lead AI Infrastructure Engineer

About the role

Avride is seeking a skilled software engineer with a leadership orientation and extensive experience in machine learning infrastructure. In this position, you will shape and guide the ML infrastructure across the organization. A key challenge involves optimizing GPU inference for both onboard applications requiring near real-time performance and offboard scenarios that demand high throughput and predictable execution.

Key facts

What you'll do

• Initially, you will focus on enhancing the GPU inference framework to improve performance.
• Subsequently, you will take on broader responsibilities for the overall ML infrastructure integrated within various ML pipelines.
• Collaborate closely with the applied ML team to define the architecture for neural models.

Requirements

• Proficient in PyTorch.
• Solid understanding of GPU functionality.
• Proven experience in identifying and resolving performance-related challenges.
• Demonstrated history of building infrastructure, particularly in distributed systems.
• At least 5 years of experience with C++.
• Experience in programming within multi-threaded environments, including managing multiple processes, threads, timers, and interrupts.

Nice to have

• Experience with simulation environments.
• Familiarity with optimizing neural network execution.

Skills & tools

• C++, PyTorch, multi-threading, distributed systems, GPU optimization.

Practical notes

Candidates must be authorized to work in the U.S. Relocation sponsorship is not available, and remote work options are not offered. Avride is an equal opportunity employer and is dedicated to providing reasonable accommodations for qualified applicants and employees with disabilities to ensure equal access to employment opportunities. If you require assistance during the application or hiring process, or need support to perform essential job functions, please reach out to jobs@avride.ai.