3 days ago
Base Salary
$124k - $242k/yr
Responsibilities
- Develop reusable performance-optimization skills, workflows, and evidence-based methodologies for autonomous AI agents.
- Benchmark and optimize AI inference throughput, latency, batching, parallelism, KV-cache usage, quantization, speculative decoding, and serving SLAs.
- Measure and improve aggregated and disaggregated serving architectures using TensorRT-LLM, SGLang, vLLM, and Dynamo on NVIDIA GPUs.
- Profile workloads with Nsight Systems, kernel traces, and internal tools, using roofline and speed-of-light analysis to identify performance opportunities.
- Review agent-generated experiments, validate findings, curate best-known configurations, and maintain rigorous reproducible comparisons.
- Contribute upstream serving-framework patches, optimized kernels, and deployment recipes while preserving model correctness.
- Collaborate with inference-framework, kernel, benchmarking, and GPU-architecture teams to deliver measured performance improvements.
Requirements
- Bachelor’s, master’s, or doctoral degree in computer science, computer engineering, electrical engineering, applied mathematics, or a related field, or equivalent experience.
- At least 3 years of relevant engineering experience.
- Extensive knowledge of AI model-execution efficiency and optimization, including continuous batching, throughput-latency tradeoffs, KV-cache and memory limitations, parallel processing, MoE serving, quantization, and serving SLAs.
- Hands-on experience benchmarking and profiling GPU workloads with Nsight Systems, Nsight Compute, CUPTI, or PyTorch Profiler and interpreting kernel-level performance data.
- Strong Python engineering skills and ability to navigate and modify large C++/CUDA serving codebases.
- Experience with controlled single-variable experiments, reproducible benchmarks, and evidence-backed optimization decisions.
- Strong written and verbal communication skills.
- Preferred experience contributing to TensorRT-LLM, vLLM, SGLang, FlashInfer, Dynamo, or comparable inference frameworks.
- Preferred experience with disaggregated serving, expert-parallel MoE inference, KV-cache transfer, or NCCL/NIXL/NVSHMEM communication at multi-node scale.
- Preferred CUDA kernel authorship or optimization experience on Hopper or Blackwell architectures, including Tensor Cores, TMA, and warp specialization.
- Preferred results on public inference benchmarks such as MLPerf Inference or SemiAnalysis InferenceX.
- Preferred experience building or operating agentic AI workflows for engineering automation.
Benefits
- Hybrid work arrangement.
- Equity eligibility and comprehensive benefits package.
- Applications accepted at least until November 13, 2026.
Categories
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.