Tech Stack
Tag name is followed by "@" symbol and proficiency level value.
About proficiency levels:
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
AI @ 7
CUDA @ 3
Communication @ 6
Deep Learning @ 4
Engineering Management @ 4
GPU @ 3
HPC
JAX @ 4
Leadership @ 4
NCCL @ 3
Networking
Performance Optimization @ 4
PyTorch @ 4
Robotics @ 4
Technical Leadership @ 4
TensorFlow @ 4
TensorRT @ 3
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
Details
JAX is the framework of choice for ambitious AI research, and the datacenters it runs on are evolving rapidly. NVIDIA supercomputers are becoming more heterogeneous, combining GPUs, CPUs, and LPUs, and JAX needs to evolve to perform well across all of them. NVIDIA seeks a Senior Engineering Manager to define and drive NVIDIA's JAX strategy, coordinating multiple teams and workstreams to ensure JAX delivers peak performance across the platform, from single-accelerator workloads to hundreds of thousands of devices on the largest supercomputers ever built.
A critical part of this role is ensuring JAX is ready on next-generation architectures, including Rubin Ultra, LPUs, and the CPUs that drive them, from day one. This requires keeping up with where AI is heading and supporting emerging needs across training, post-training, inference, and robotics while bridging new hardware capabilities with AI trends.
Responsibilities
- Drive the engineering contribution strategy across the JAX ecosystem stack, including JAX core, XLA, Shardy, MPMD, and application-level codebases such as MaxText. Prioritize NVIDIA's contributions to maximize performance, adoption, and ecosystem influence.
- Promote teamwork across organizational boundaries to shape NVIDIA's AI platform across compiler, runtime, networking, and hardware teams, including XLA, TileIR, CUDA, and related groups.
- Build deep partnerships with key open-source projects, especially Google's JAX team, supporting partners while representing NVIDIA's interests in shaping the project's direction.
- Design processes and define clear success criteria to keep teams aligned to outcomes.
- Build staffing plans, review team capacity, and make strategic hiring decisions to address current and future needs.
- Lead, grow, and mentor a high-performing engineering organization by developing technical leaders and creating opportunities to experiment, prototype, and build innovative systems that improve products and processes.
Requirements
- MS or PhD in Computer Science, Computer Engineering, or a related field, or equivalent experience.
- 10 or more years of overall software engineering experience, with 4 or more years in engineering management or technical leadership.
- Strong technical background in system software, compilers, high-performance computing, or AI frameworks.
- Proven experience leading domain-level strategy and projects spanning organizational boundaries, building consensus, influencing without direct authority, and tailoring communication to audiences ranging from engineers to executives.
- Track record of owning outcomes across multiple projects and teams, balancing trade-offs, and driving progress with incomplete information.
- Experience identifying development-cycle gaps and defining workflows across teams and organizations to improve efficiency.
- Experience leading teams that contribute to large-scale projects with external collaborators.
Preferred Qualifications
- Hands-on experience with JAX and systems such as XLA, HLO, PJRT, Shardy, or JAX's tracing and transformation system.
- Experience leading teams working on compiler or runtime infrastructure for deep learning frameworks such as JAX, PyTorch, TensorFlow, or equivalent.
- Familiarity with NVIDIA's AI platform components, including GPU programming, CUDA, cuDNN, NCCL, TensorRT, Transformer Engine, and heterogeneous compute targets such as GPUs, CPUs, and LPUs.
- Experience driving performance optimization for large-scale distributed AI training, post-training such as RLHF and alignment, inference, or robotics workloads across multiple nodes and GPUs.
- Experience driving framework or software bring-up on new hardware architectures while coordinating across silicon, driver, compiler, and framework teams.
Compensation and Benefits
The base salary range is $272,000-$431,250 USD, determined based on location, experience, and the pay of employees in similar positions. The role also includes eligibility for equity and benefits.
Applications will be accepted at least until April 10, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes. NVIDIA is committed to fostering a diverse work environment and is an equal opportunity employer.