Software Engineer – AI Inference Integration and Optimization
No visa sponsorship
Core
Develop, integrate, and optimize AI inference software for AMD platforms.
Role type
Software Engineer (AI Inference)
Builds
AI inference software for AMD hardware platforms
Domain
Semiconductor / AI Infrastructure
Deliverable
production ML models
Required skills
C/C++, Python, software profiling, debugging, automated testing, performance benchmarking
Preferred skills
AI frameworks, inference runtimes, PyTorch, ONNX Runtime, ROCm, HIP, GPU programming
Technologies
PyTorch, ONNX Runtime, ROCm, HIP
Responsibilities
Develop and integrate AI inference software; Debug functional and performance issues; Optimize workloads for latency, throughput, and memory efficiency; Build automated tests and performance benchmarks
Seniority
Individual Contributor