NVIDIA

Senior Deep Learning Compiler Engineer - PyTorch

292.5k - 507k PLN292 500 - 507 000 PLN/ mies./ mies.UoPUmowa o pracę (brutto)

SeniorHybryda·BerlinFull-time·Umowa o pracę

#259647·Dodano 10 miesięcy temu·8

Źródło: NVIDIA

Aplikuj teraz

Tech Stack / Keywords

PyTorchAIGitHubCUDAPython

Firma i stanowisko

NVIDIA is developing Thunder, a source-to-source compiler designed to optimize performance for PyTorch models on NVIDIA GPUs. The team works closely with frameworks such as PyTorch 2.0's TorchDynamo and TorchInductor, collaborating with compiler, library, and systems experts including those behind nvFuser, TVM, XLA, and CUDA to deliver high-impact open-source solutions.

Wymagania

Bachelor's, Master's, or Ph.D. in Computer Science or related technical field, or equivalent experience.
8+ 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.
Solid foundation in compiler concepts including abstract syntax trees (ASTs), intermediate representations (e.g., SSA form), program analysis, and code generation.
Excellent communication and collaboration skills for distributed, open-source environments.

Nice to have:

Previous contributions to deep learning compiler projects like TVM, MLIR, IREE or to deep learning frameworks.
Deep expertise in PyTorch internals, especially its compiler stack (TorchDynamo, TorchInductor).
Experience with JAX-like functional transformations in compiler contexts.
Familiarity with parallel programming, distributed systems, and high-performance CUDA coding.
Active participation in open-source communities through code contributions, design discussions, or mentorship.

Obowiązki

Lead design, implementation, optimization, and maintenance of core compiler technologies for accelerated deep learning workloads.
Collaborate with engineers who developed PyTorch for NVIDIA hardware to pioneer new features.
Perform performance analysis on workloads running across thousands of GPUs to identify optimization opportunities.
Work closely with compiler, library, and systems teams including experts behind nvFuser, TVM, XLA, and CUDA to translate research into practical solutions.
Contribute to the development and enhancement of the Thunder compiler and PyTorch ecosystem.

Benefity

Highly competitive salaries.
Extensive benefits package.
Work environment promoting diversity, inclusion, and flexibility.

Elastyczne godziny

NVIDIA

20 aktywnych ofert

Zobacz wszystkie oferty

Aplikuj teraz