Senior Software Engineer - AI Inference Performance

NVIDIA; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Job summary

NVIDIA seeks a Senior Software Engineer – AI Inference Performance to push LLM/VLM workloads toward practical performance limits on NVIDIA GPUs. You will lead end-to-end analysis, build performance models, and optimize latency, throughput, and energy efficiency across models, serving software, and distributed runtimes.

The role spans profiling, tuning, and developing high-performance kernels with CUDA, Triton, and CUTLASS while collaborating with model, kernel, networking, and GPU architecture

Qualifications

• 6+ years of experience in full-stack LLM/VLM inference performance.
• Strong programming skills in Python, Rust and/or C++, with CUDA experience.
• Expertise in speed-of-light analysis, roofline models, microbenchmarks, and profiling tools.

Responsibilities

• Lead end-to-end analysis of LLM/VLM inference processes and optimize latency, throughput, and KV-cache.
• Build performance models and translate profiling data into actionable optimizations.
• Profile workloads with Nsight Systems, Nsight Compute, and PyTorch Profiler; remove bottlenecks in host, CUDA kernels, memory, and scheduling.
• Tune serving parameters (batching, KV-cache management, quantization, speculative decoding, CUDA Graphs, model parallelism).
• Develop performance-critical kernels (attention, matrix multiply, mixture-of-experts routing) using CUDA/CUTLASS/Triton.
• Establish benchmarks, run records, and regression gates; collaborate across teams to upgrade TensorRT-LLM, vLLM, SGLang, etc.

Skills

Python

C++

Rust

CUDA

Education

BS or MS in CS/CE or related field

Tools

NVIDIA Nsight Systems

Nsight Compute

PyTorch Profiler

CUDA

Job description

NVIDIA is the platform upon which every new AI-powered application is built. We are seeking a Senior Software Engineer -- AI Inference Performance to advance innovative LLM and VLM inference. You will push workloads toward practical performance limits on NVIDIA GPU-accelerated systems. Your work will span models, serving software, distributed runtimes, communication, CUDA kernels, and GPU architecture. Deliver measurable gains in latency, throughput, efficiency, and scale. This is a hands-on role for an engineer who turns performance models and profiler data into working code. You will collaborate with model, framework, kernel, networking, and GPU architecture teams. You will contribute improvements to open-source inference engines and develop methods that others can reproduce. Your work will improve production deployments and help build future NVIDIA platforms.

What you'll be doing:

• Lead end-to-end analysis of LLM/VLM inference processes. Define representative prefill and decode workloads. Optimize time to first token, inter-token latency, P99 end-to-end latency, processing efficiency, and key-value (KV) cache capacity. For multimodal models, isolate preprocessing, encoder, and decoder costs.
• Build speed-of-light and roofline models to quantify performance headroom. Connect arithmetic intensity, bandwidth, occupancy, memory hierarchy, and communication costs to clear optimization hypotheses.
• Profile workloads using NVIDIA Nsight Systems, Nsight Compute, PyTorch Profiler, and custom instrumentation. Eliminate bottlenecks in host code, CUDA kernels, memory, communication, and scheduling.
• Tune serving hyperparameters and techniques such as batching, KV-cache management, quantization, speculative decoding, CUDA Graphs, and model parallelism. Choose them based on workload, hardware, model quality, and service-level objectives.
• Build and optimize performance-critical kernels, including attention, matrix multiplication, mixture-of-experts routing, quantization, and data movement. Use CUDA, CUTLASS, Triton, or related technologies.
• Establish repeatable benchmarks, canonical run records, and performance regression gates. Manage aspects such as model, precision, hardware, topology, software, features, and workload; Balance between performance and accuracy. Collaborate across with various teams and contribute high-quality upgrades to TensorRT-LLM, vLLM, SGLang, or associated projects.

What we need to see:

• More than 6 years of experience in full-stack LLM/VLM inference performance involving models, serving, distributed runtimes, kernels, and hardware. Your efforts result in measurable gains in production or production-representative environments.
• Strong programming skills in Python, Rust and/or C++, plus hands-on experience with CUDA or another GPU programming environment.
• Demonstrated expertise in speed-of-light analysis, roofline models, microbenchmarks, and tools including NVIDIA Nsight Systems and Nsight Compute. You convert profiles into testable hypotheses and validated progress.
• Deep understanding of GPU architecture, including Tensor Cores, memory hierarchy, caches, occupancy, synchronization, and numerical formats across hardware generations.
• Practical experience optimizing inference servers and model execution. You can choose techniques for the workload, including batching, scheduling, KV-cache management, quantization, speculative decoding, and various parallelism strategies.
• Understanding of distributed systems and networking for accelerated computing. You can reason about collectives, topology, and scale-up versus scale-out performance.
• BS or MS in Computer Science, Computer Engineering, or a related field, or equivalent experience.

Ways to stand out from the crowd:

• Contributions to one or more high-performance AI projects. Examples include TensorRT-LLM, vLLM, SGLang, PyTorch, CUDA, Triton, or NCCL.
• Experience developing AI-agent-supported performance workflows that automatically gather and analyze profiles, identify bottlenecks, explore serving configurations, or produce optimized runtime and kernel code. You validate generated changes through reproducible, human-reviewed tests for performance, model quality, and correctness.
• Published research, conference presentations, technical talks, or blog posts that clearly explain inference performance methods and results.
• Delivered advancements for new LLM or VLM architectures, long-context inference, mixture-of-experts models, multimodal pipelines, or large-scale distributed serving.

Successfully carrying these out will shape the future of AI inference performance! With competitive salaries and a generous benefits package (www.nvidiabenefits.com ), we are widely considered to be one of the technology world's most desirable employers. We have some of the most forward-thinking and hardworking people in the world working for us and, due to outstanding growth, our best-in-class engineering teams are rapidly growing. If you're a creative and autonomous engineer with a real passion for technology, we want to hear from you! Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 184,000 USD - 287,500 USD for Level 4, and 224,000 USD - 356,500 USD for Level 5. You will also be eligible for equity and benefits. Applications for this job will be accepted at least until August 30, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes. NVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.