AI Inference Performance Engineer

Details

We optimize and benchmark GenAI inference on NVIDIA's latest accelerators, defining industry performance standards across language models, video generation, and speech workloads. The team works directly with TensorRT-LLM, SGLang, and vLLM, building tools to evaluate serving performance at scale. This role sits at the intersection of GPU performance engineering and public accountability.

Responsibilities

• Drive industry benchmark results: own the end-to-end optimization pipeline and implement/integrate optimizations in quantization, scheduling, memory management, and distributed inference across TensorRT-LLM, SGLang, and vLLM.
• Define and optimize cutting-edge workloads: identify and shape next-generation inference benchmarks, multi-turn coding, agentic workflows, and other emerging AI use cases. Collaborate with framework and kernel teams to push performance on large-scale LLM-MoE models, vision-language models, video diffusion models, recommendation, and speech workloads.
• Architect distributed inference: design and optimize execution from single-GPU to rack-scale clusters, managing performance across GPU clusters.
• Establish performance methodology: apply roofline analysis and systematic profiling to decompose bottlenecks across CUDA kernels, frameworks, and serving layers.
• Influence the ecosystem: contribute to TensorRT-LLM, vLLM, SGLang, and other open-source projects. Partner with architecture, kernel, and compiler teams to shape GPU roadmaps based on real workload data.
• Technical leadership: raise the technical bar for the team, drive cross-functional execution on tight benchmark timelines, and lead a world-class team.

Requirements

• BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or equivalent experience.
• 5+ years of relevant software development experience.
• Strong Python or C++ programming, software design, and software engineering skills.
• Expertise with a deep-learning framework such as PyTorch or JAX.
• Proven track record of delivering measurable performance improvements in deep learning inference or high-performance systems.
• Deep understanding of LLM/VLM architectures and inference mechanics: attention, KV caching, batching strategies, decode-phase bottlenecks, speculative decoding, disaggregated serving, etc.

Ways To Stand Out

• Prior experience with an LLM framework (TensorRT-LLM, vLLM, SGLang, etc.) or a DL compiler in inference, deployment, algorithms, or implementation.
• Prior experience with performance modeling, profiling, debugging, and code optimization of DL/HPC/high-performance applications.
• Experience with scale-out inference orchestration (MPI, NCCL, Kubernetes) on large GPU clusters.
• Expertise in kernel development (CUTLASS, cuteDSL, tilelang, OpenAI Triton) or compiler/runtime paths (torch.compile, graph lowering, operator fusion). Architectural knowledge of CPU, GPU, FPGA or other DL accelerators; GPU programming experience (CUDA).
• Track record of leading ambiguous, high-impact technical programs across multiple teams under tight deadlines.

Benefits

• Eligible for equity and company benefits (link to benefits page provided in the original posting).

Additional information

• Office policy: Hybrid (#LI-Hybrid).
• Location: Santa Clara, California, United States.
• Employment type: Full time.
• Application deadline: at least until March 13, 2026.
• Salary: base salary range is 152,000 USD - 241,500 USD. NVIDIA uses AI tools in its recruiting processes. NVIDIA is an equal opportunity employer.