AI Systems Engineer – AI Model (Training & Inference)
Core
Own the end-to-end model execution stack on AMD Instinct GPUs, spanning large-scale training infrastructure and high-performance inference serving.
Role type
Senior Software Development Engineer (AI Systems)
Builds
Training infrastructure for LLMs/VLMs/MoE and optimized inference serving frameworks for AMD Instinct GPUs
Domain
High-Performance Computing (HPC) and AI/ML Systems
Deliverable
production ML models
Required skills
GPU kernel optimization, distributed training orchestration, RCCL communication patterns, inference serving frameworks, quantization pipelines, observability tooling
Preferred skills
Frontier model deployment, AMD Instinct architecture expertise, open-source AI framework contributions, pre-silicon software validation
Technologies
HIP, Triton, MLIR, ROCm, Kubernetes, vLLM, SGLang, DeepSpeed, Megatron-LM, RCCL
Responsibilities
Enable and optimize large-scale model training on GPU clusters; Write and optimize high-performance GPU kernels for inference; Build quantization pipelines for production deployment; Develop monitoring and validation infrastructure for GPU clusters
Seniority
Senior, hands-on IC
