Join our dynamic XLA team at NVIDIA to develop high-performance compiler optimization algorithms for deep learning workloads on JAX and the OpenXLA compiler. You will focus on enhancing inference and training performance for NVIDIA GPUs by crafting advanced graph partitioning techniques, tensor sharding methods, and efficient code generation using MLIR, LLVM, and OpenAI Triton. This role involves collaborating with hardware engineering teams to design AI compiler features for future GPUs while also contributing to user-facing JAX library improvements. Ideal candidates possess a strong background in computer science or related fields, 4+ years of experience in performance analysis and compiler optimizations, and expertise in C/C++ programming, GPU architecture, and high-performance computing. Experience with XLA, MLIR, LLVM, and deep learning frameworks like JAX is highly valued.
Develop compiler optimization algorithms for deep learning workloads on NVIDIA GPUs.
Design and implement graph partitioning and tensor sharding techniques for distributed training.
Perform performance tuning and analysis to enhance inference and training efficiency.
Generate code for NVIDIA GPU backends using open-source compilers like MLIR and LLVM.
Collaborate with hardware engineering teams to design AI compiler features for future GPUs.
Craft user-facing features in JAX and related libraries, focusing on software engineering excellence.
What we're looking for
4+ years of relevant work or research experience in performance analysis and compiler optimizations.
Strong C/C++ programming skills and software design expertise.
Deep understanding of CPU and GPU architectures for high-performance computing.
Experience with deep learning frameworks like JAX, PyTorch, or TensorFlow.
Familiarity with open-source compilers such as XLA, MLIR, LLVM, and Triton.
Ability to work independently on complex projects and lead development efforts.
Market check
Salary context
This
$152,000–$241,500
range sits above
41%
of similar postings on FindRole.
Peer median band
$168,000–$260,500
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$185,187–$235,750
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
Employer
About Nvidia
Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing
Nvidia currently has
801 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 797 roles with salary data.