Software Engineer Systems Machine Learning – Frameworks

Meta; Bellevue (WA); On-site; USD 122,000 - 181,000; Full time

Job summary

Meta in Bellevue, WA seeks a Software Engineer for Inference Enablement within the PyTorch AI framework ecosystem. You will help build the foundational technology enabling state-of-the-art models across Ads, Reels, Feed, and GenAI, with hardware acceleration on CPU, GPU, and silicon.

The role emphasizes development of AI frameworks, compilers, and high-performance kernels, with opportunities to optimize model architectures and contribute to cutting-edge inference and training tooling.

Qualifications

• Python and C/C programming skills.
• Experience in AI framework development or accelerating deep learning models on hardware architectures.
• Must obtain work authorization in country of employment at the time of hire and maintain ongoing work authorization during employment.

Responsibilities

• Develop software stack focusing on AI frameworks, compiler stack, high-performance kernel development and acceleration for next-generation AI accelerators.
• Contribute to PyTorch core compilers to support new hardware accelerators and optimize performance.
• Analyze neural networks and implement compiler optimization algorithms.
• Accelerate next-gen deep learning models (recommendation systems, GenAI, CV, NLP).
• Performance tuning of deep learning framework and software components.

Skills

Python programming

C/C++ programming

AI framework development

Hardware acceleration

Education

BSc in CS/EE or related

Tools

Triton

CUDA

Job description

Summary:

You will be a member of the Inference Enablement Team and part of the bigger PyTorch AI framework organization. We build the foundational technology and frameworks that enable and optimize state-of-the-art model architectures on new hardware. We work with many different types of model architectures across Ads, Reels, Feed, Marketplace, IG, and GenAI. We support the enablement of models on all kinds of hardware as well, including CPU, GPU, and custom Silicon. We build the model publishing frameworks and platforms to accomplish this at scale for a large, broad set of models that are pushing the state of the art in Inference. Our work involves a blend of software systems and ML, and you’ll have the opportunity to learn about how PyTorch works at a more in-depth level as well. We play an integral role in helping Meta ship the most important, state-of-the-architectures? including models with significant Ads Revenue gain, Reels Watch Time gain, all while saving multiple MegaWatts of power through our efficiency work.

Required Skills:

Software Engineer Systems Machine Learning – Frameworks Responsibilities:

1. Development of software stack with one of the following core focus areas: AI frameworks, compiler stack, high performance kernel development and acceleration onto next generation of AI Accelerators architectures

2. Contribute to the development of the PyTorch AI framework core compilers to support new state of the art inference and training AI hardware accelerators and optimize their performance

3. Analyze neural networks, develop & implement compiler optimization algorithms

4. Accelerate the next generation of deep learning models such as Recommendation systems, Generative AI, Computer vision, NLP etc

5. Performance tuning and optimizations of deep learning framework & software components

Minimum Qualifications:

Minimum Qualifications:

1. Python and C/C programming skills

2. Experience in AI framework development or accelerating deep learning models on hardware architectures

3. Must obtain work authorization in country of employment at the time of hire and maintain ongoing work authorization during employment

Preferred Qualifications:

Preferred Qualifications:

1. Experience adhering to and implementing responsible, ethical AI practices (e.g., risk assessment, bias mitigation, quality and accuracy reviews)

2. OR AI Compiler: Experience with compiler optimizations such as loop optimizations, vectorization, parallelization, hardware specific optimizations such as SIMD. Experience with MLIR, LLVM, IREE, XLA, TVM, Halide is a plus

3. Demonstrated ongoing AI skill development (e.g., prompt/context engineering, agent orchestration) and staying current with emerging AI technologies

4. Experience working with kernel frameworks like Triton, or CUDA

5. OR AI frameworks: Experience in developing training and inference framework components. Experience in system performance optimizations such as runtime analysis of latency, memory bandwidth, I/O access, compute utilization analysis and associated tooling development

6. Knowledge of GPU, CPU, or AI hardware accelerator architectures

7. Demonstrated ability to integrate AI tools to optimize/redesign workflows and drive measurable impact (e.g., efficiency gains, quality improvements)

Public Compensation:

$121,992/year to $181,000/year bonus equity benefits

Industry:

Internet

Equal Opportunity:

Meta is proud to be an Equal Employment Opportunity and Aff We do not discriminate based upon race, religion, color, national origin, sex (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender, gender identity, gender expression, transgender status, sexual stereotypes, age, status as a protected veteran, status as an individual with a disability, or other applicable legally protected characteristics. We also consider qualified applicants with criminal histories, consistent with applicable federal, state and local law. Meta participates in the E‑Verify program in certain locations, as required by law. Please note that Meta may leverage artificial intelligence and machine learning technologies in connection with applications for employment.

Meta is committed to providing reasonable accommodations for candidates with disabilities in our recruiting process. If you need any assistance or accommodations due to a disability, please let us know at [e-mail].