Senior Deep Learning Software Engineer, Inference and Model Optimization

What you'll do

• Develop and deploy generative AI models and build automated model-graph extraction and deployment solutions.
• Create inference optimizations, including model sharding and efficient attention kernels; profile GPU performance.
• Architect a modular, scalable software platform and collaborate across teams to integrate performant kernels.

What they ask for

• Master’s, PhD, or equivalent experience in Computer Science, AI, Applied Math, or a related field.
• 8+ years of relevant work or research experience in Deep Learning.
• Strong proficiency in Python, PyTorch, and related ML tools (e.g. HuggingFace).
• Excellent software design skills, including debugging, performance analysis, and test design; strong algorithms and programming fundamentals.

Nice to have

• Contributions to PyTorch, JAX, or other Machine Learning Frameworks; knowledge of GPU architecture and compilation stack.
• Familiarity with NVIDIA deep learning SDKs such as TensorRT, or experience writing high-performance GPU kernels using CUDA, CUTLASS, or Triton.

Pay

184,000 USD - 287,500 USD (base salary, Level 4); 224,000 USD - 356,500 USD (base salary, Level 5)

Tools

PyTorch, HuggingFace, TorchDynamo, torch.export, torch.compile, CUDA, TRT-LLM, Triton

AI focus

Optimize generative AI models, including LLMs and diffusion models, for inference efficiency and automated deployment; develop model optimization and inference software.