This role pays more than
94%
of similar roles. Most pay
$151,000–$203,723
— the shaded band above.
At the midpoint, this role pays about
$255k
versus about
$177k
for comparable roles.
Based on 240 similar postings.
Employer
About Amd
AMD (Advanced Micro Devices) is a semiconductor company that develops high-performance processors, graphics cards, and adaptive computing solutions for gaming, data centers, and embedded markets. Industry: Semiconductors
Amd currently has
367 open roles
on FindRole.
Listed pay typically runs
$166,400–$249,600
across 367 roles with salary data.
As a Post-Training Platform Infrastructure Engineer, you will join the team to focus on post-training and inference infrastructure, specifically addressing P/D disaggregation, KV cache lifecycle management, and efficient offloading mechanisms. You will research and analyze modern LLM inference frameworks to identify performance bottlenecks in latency, throughput, and memory pressure while developing infrastructure-level features for multi-GPU and multi-node deployments. The role also involves applying a research-driven approach to RL systems to optimize policy rollout and memory usage during training. To succeed, you must possess expertise in distributed systems, GPU-accelerated workloads, and memory-constrained environments. You will utilize Python and C++ to modify complex open-source codebases while leveraging profiling tools for CPU and GPU performance analysis. Your work solves critical challenges in large-scale model inference and reinforcement learning pipelines.
LLM
PyTorch
Python
Triton-Inference Server
vLLM
SGLang
CUDA
Triton
torch.compile
torchDynamo
Distributed Systems
Kernel Design
Deep Learning
KV-Cache Management
Model Optimization
VMware
Linux
Windows Server
Ansible
Terraform
PowerShell DSC
TCP/IP
DNS
DHCP
Active Directory
ServiceNow
Infrastructure Monitoring
Configuration Management
Networking