Senior AI Performance Engineer - LLM Inference (vLLM)

AMD; Helsinki; On-site; 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 looking for a performance-obsessed senior engineer to push AI inference performance to the limit on AMD GPUs, with vLLM as the primary serving framework. You will work end-to-end across the stack: profiling, diagnosing, and optimizing leading models running on vLLM across customer-relevant serving configurations (e.g. agentic coding, long-context, high-throughput serving). You will own hard performance problems on our most strategic customer engagements and leave behind measurable uplifts and reusable methodology.

KEY RESPONSIBILITIES:

• Drive performance optimization end-to-end on vLLM across leading models and customer-relevant serving configurations, closing competitive gaps through kernel and systems-level optimizations
• Profile, diagnose, and resolve cross-stack performance bottlenecks in vLLM deployments, from GPU kernels and operator dispatch to the vLLM scheduler, PagedAttention/KV cache management, and multi-node communication
• Diagnose kernel-level performance issues using profiling tools: identify occupancy limitations, L2 cache thrashing, register pressure, memory coalescing issues, etc, and translate findings into actionable optimizations
• Contribute to customer-facing technical engagements: present findings, recommend optimizations, and deliver measurable performance uplifts on vLLM
• Integrate and optimize custom kernels (Triton, Gluon, CK, PyDSL, ASM, AITER) within vLLM, understanding dispatch paths, shape extraction, and backend selection
• Optimize multi-node distributed inference on vLLM: communication-compute overlap, parallelism strategies (TP/PP/EP/DP), and scale-out performance
• Contribute to shared performance optimization methodology that raises the bar across the team
• Leverage AI agents to accelerate daily work and help define best practices for AI-assisted performance engineering
• Upstream optimizations into vLLM and adjacent open-source frameworks such as SGLang and PyTorch

PREFERRED EXPERIENCE:

• 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, chunked prefill, ROCm backend integration); familiarity with SGLang, TensorRT-LLM, or similar is a plus
• Strong background in end-to-end workload profiling and bottleneck diagnosis
• Understanding of GPU kernel performance characteristics: occupancy, register and LDS pressure, memory coalescing, cache utilization, wavefront scheduling, and instruction-level bottlenecks
• Ability to read and reason about kernel-level profiling data and translate it into concrete optimization actions
• Understanding of model architectures (transformers, MoE, diffusion), inference paradigms (speculative decoding, prefill-decode disaggregation, continuous batching), and how they map to hardware and to vLLM's execution model
• Experience with custom kernel development or integration (HIP, CUDA, Triton, CK, or similar)
• Understanding of multi-GPU and multi-node distributed systems: scale-up and scale-out topologies, RCCL/NCCL, RDMA, and communication-compute overlap
• Strong proficiency in Python and C++
• Ability to engage with customers, present findings, and support technical decisions
• Fluent in AI-assisted development: daily user of AI agents and tools
• Strong Linux systems knowledge
• Excellent written and verbal English communication skills

ACADEMIC CREDENTIALS:

Master's, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or equivalent. Advanced degree preferred but exceptional industry experience valued equally.

LOCATION:

Helsinki, Finland or Stockholm, Sweden. 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, chunked prefill, ROCm backend integration), Strong background in end-to-end workload profiling and bottleneck diagnosis, Understanding of GPU kernel performance characteristics (occupancy, register/LDS pressure, memory coalescing, cache utilization), Ability to reason about kernel-level profiling data and translate it into optimizations, Understanding of model architectures (transformers, MoE, diffusion) and inference paradigms, Experience with custom kernel development or integration (HIP, CUDA, Triton, CK, or similar), Understanding of multi-GPU and multi-node distributed systems (RCCL/NCCL, RDMA), Strong proficiency in Python and C++, Strong Linux systems knowledge, Excellent written and verbal English communication skills