Lead AI Infrastructure Engineer

Location: Austin, Texas; onsite only. Candidates must be authorized to work in the U.S. Remote work is not available.

Company

hirify.global develops self-driving technology and the infrastructure powering autonomous driving systems.

What you will do

• Own and improve the GPU inference framework, initially focusing on performance.
• Optimize onboard inference for stable near-real-time latency guarantees.
• Improve offboard inference for high throughput and deterministic execution in simulation.
• Take responsibility for broader ML infrastructure across distributed ML pipelines.
• Collaborate closely with the applied ML team on neural network architecture.

Requirements

• Experience with PyTorch and a strong understanding of GPU operation.
• Experience diagnosing and resolving performance issues.
• Strong infrastructure engineering experience, including distributed systems.
• 5+ years of experience with C++.
• Experience programming in multithreaded environments involving processes, threads, timers, and interrupts.
• Authorization to work in the U.S. is required.

Culture & Benefits

• Work on the core infrastructure layer of a self-driving stack.
• Collaborate across ML infrastructure and applied ML teams.
• Relocation and visa sponsorship are not offered.
• Equal opportunity employment and reasonable accommodations are provided for qualified applicants and employees with disabilities.