Software Engineer – AI Inference and Performance Optimization
amdAustin (TX)
Software Engineer – AI Inference and Performance Optimization
Posted today
amdAustin (TX)
SENIORITY
Lead
About the role
Overview:
In this role you will develop and optimize AI inference software for AMD platforms, collaborating with architecture and engineering teams to improve performance, efficiency and scalability of AI workloads. You will build benchmarks and tests to track progress and drive practical improvements. You’ll work in a cross-functional environment to ship optimized runtimes that power AI applications. This is an opportunity to shape AI performance on cutting-edge hardware and contribute to AMD’s mission of advancing technology.
Responsibilities:
Develop and optimize AI inference software, runtimes, and workloads Identify bottlenecks and improve latency, throughput, and memory efficiency Integrate and validate improvements with architecture and software teams Build benchmarks and automated tests to track performance and correctness
Key requirements:
Strong C/C++ development skills Strong Python development skills Experience with AI frameworks, inference runtimes, and performance profiling Familiarity with GPU programming, parallel computing, and memory optimization Experience with PyTorch, ONNX Runtime, ROCm, HIP, or similar technologies collaborative problem-solving ability to turn performance analysis into practical improvements C/C++ Python AI frameworks and inference runtimes
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.