Lead AI Infrastructure Engineer (AI)

TL;DR

Lead AI Infrastructure Engineer (AI): Building and optimizing the base infrastructure layer for a self-driving autopilot stack with an accent on GPU inference performance and deterministic execution. Focus on developing C++ frameworks for autonomy components, optimizing throughput for simulations, and scaling ML pipelines across the company.

Location: Austin, Texas. Must be authorized to work in the U.S. (No relocation sponsorship, no remote options).

Company

hirify.global develops an advanced self-driving stack for autonomous vehicle autopilot systems.

What you will do

• Lead the development and optimization of the GPU inference framework to ensure near real-time guarantees for onboard applications.
• Take ownership of the broader ML infrastructure distributed across various ML pipelines.
• Collaborate closely with applied ML teams to define neural model architectures.
• Build and optimize execution graphs and runtimes for both onboard and simulation environments.

Requirements

• 5+ years of professional experience with C++.
• Strong experience with PyTorch and a deep understanding of GPU architecture.
• Proven track record of building distributed systems and diagnosing performance issues.
• Programming experience in multi-threaded environments (multiple processes, threads, timers, and interrupts).
• Must be authorized to work in the U.S.