Senior Deep Learning Compiler Engineer - PyTorch

at Nvidia

📍 Berlin, Germany

PLN 292,500-507,000 per year

SENIOR

✅ On-site

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 CUDA @ 3 Communication @ 6 Deep Learning @ 4 Distributed Systems @ 3 GPU GitHub JAX @ 4 Parallel Programming @ 3 Performance Analysis PyTorch @ 4 Python @ 7

Details

Join NVIDIA at the forefront of AI compiler technology and help build the next generation of tools used by AI developers and researchers worldwide. The team is developing Thunder, a source-to-source compiler designed to unlock outstanding performance for PyTorch models on NVIDIA GPUs. The role contributes to the PyTorch ecosystem through modern compiler stacks such as PyTorch 2.0's TorchDynamo and TorchInductor.

Responsibilities

Lead the design, implementation, optimization, and maintenance of core compiler technologies that accelerate large-scale deep learning workloads.
Contribute to the future of accelerated AI and compiler innovation.
Collaborate with engineers who built PyTorch for NVIDIA hardware to develop new features and advance framework capabilities.
Perform performance analysis on workloads running across thousands of GPUs to identify optimization opportunities and inform the future design of Thunder.
Work with compiler, library, and systems teams involved in nvFuser, TVM, XLA, and CUDA.
Translate the latest research into practical, high-impact open-source solutions.

Requirements

Bachelor's, Master's, or Ph.D. in Computer Science or a related technical field, or equivalent experience.
8 or more years of relevant work experience.
Strong command of Python and experience building complex, well-tested software systems.
Hands-on experience with deep learning frameworks such as PyTorch or JAX.
Strong foundation in compiler concepts, including abstract syntax trees, intermediate representations such as SSA form, program analysis, and code generation.
Excellent communication and collaboration skills for working in a distributed, open-source environment.

Preferred Qualifications

Contributions to deep learning compiler projects such as TVM, MLIR, or IREE, or to deep learning frameworks.
Deep expertise in PyTorch internals, particularly TorchDynamo and TorchInductor.
Experience with JAX-like functional transformations and their application in a compiler context.
Familiarity with parallel programming, distributed systems, and high-performance CUDA development.
Impactful participation in open-source communities through code contributions, design discussions, or mentorship.

Benefits

NVIDIA offers highly competitive salaries, an extensive benefits package, and a diverse, inclusive, and flexible work environment. NVIDIA is an equal opportunity employer committed to fostering a supportive and empowering workplace.

The base salary is determined based on location, experience, and the pay of employees in similar positions. For Poland, the base salary range is 292,500 PLN–507,000 PLN.