Senior AI Inference Performance Engineer (LLM)

AMD; Helsinki; Hybrid; EUR 140,000 - 200,000; Full time

Job summary

AMD is seeking a senior engineer to push AI inference performance on GPUs using vLLM as the primary serving framework. You will own hard performance problems across the stack, profiling, diagnosing, and optimizing models on customer-engaged deployments, delivering measurable uplifts and reusable methodologies.

You will work end-to-end across profiling, kernel and system-level optimizations, contributing to shared performance methodologies and accelerating daily work with AI agents.

Qualifications

• 5+ years of software development experience in GPU computing, AI systems, or high-performance computing.
• Hands-on experience with vLLM internals (V1 engine, scheduler, PagedAttention/KV cache manager).
• Strong profiling and bottleneck-diagnosis background across GPU kernels and system software.
• Ability to translate profiling data into concrete optimizations and improvements.

Responsibilities

• Drive performance optimization end-to-end on vLLM across leading models and configurations.
• Profile, diagnose, and resolve cross-stack performance bottlenecks from GPU kernels to vLLM scheduler.
• Diagnose kernel-level issues and translate findings into actionable optimizations.
• Present findings and deliver measurable performance uplifts for customer engagements.
• Integrate and optimize custom kernels within vLLM and related open-source frameworks.

Skills

GPU computing

AI systems

End-to-end profiling

Python

C++

Kernel optimization

RDMA

Multi-node

Education

Master's in CS/CE

Tools

HIP

CUDA

Triton

CK

Gluon

SGLang

PyTorch

Job description

AMD is seeking a senior engineer to push AI inference performance on GPUs using vLLM as the primary serving framework. You will own hard performance problems across the stack, profiling, diagnosing, and optimizing models on customer-engaged deployments, delivering measurable uplifts and reusable methodologies.

You will work end-to-end across profiling, kernel and system-level optimizations, contributing to shared performance methodologies and accelerating daily work with AI agents.