Lead AI Infrastructure Engineer

Job Description

Lead the development and optimization of the GPU inference framework for both onboard real-time applications and offboard high-throughput systems. Take ownership of the broader ML infrastructure and collaborate with applied ML teams to define neural model architectures.

Requirements: Requires over 5 years of C++ experience and proficiency in PyTorch and multi-threaded environments. Candidates must have a strong background in building distributed systems and diagnosing GPU performance issues.

Key Skills: PyTorch, GPU Inference, C++, Distributed Systems, Multi-threaded Programming, ML Infrastructure, Performance Optimization, Neural Network Operations