AI Performance Engineer
… · South Plainfield, NJ, United States ·
COMPENSATION
Salary available to subscribersListed on WeAreDevelopers
- Senior AI Performance Role
- Python and C++ Expertise
- GPU & Distributed Systems
- W2 Employment Only
- H1B Transfer Supported
Join the company as an AI Performance Optimization Engineer focused on maximizing throughput, minimizing latency, and reducing costs for large-scale AI systems. You will work across the full stack, from low-level kernel optimization to distributed system tuning, ensuring rigorous data-driven decisions for production AI workloads.
What you'll do
- profile and optimize end-to-end AI training and inference pipelines
- identify and eliminate bottlenecks in data loading and model compute
- implement quantization, sparsity, and pruning strategies for efficiency
Loading…