AI Computing Software Developer - New College Graduate 2027
Core
Develop high-performance AI inference systems for Large Language Models, Recommender Systems, and Generative AI on NVIDIA GPUs.
Role type
AI Computing Software Development Engineer (Intern)
Builds
High-performance LLM inference pipelines and TensorRT compiler backends
Domain
AI Computing / GPU Acceleration
Deliverable
production ML models
Required skills
Python, PyTorch, C++, GPU programming, compiler optimization, LLM inference operations, graph transformations, operator fusion, memory optimization
Preferred skills
Experience with CUDA, deep learning software performance, multi-GPU model serving
Technologies
TensorRT, TensorRT-LLM, PyTorch, CUDA, NVIDIA GPUs
Responsibilities
Build and enhance high-performance LLM inference pipelines; Analyze and optimize LLM model execution, scalability, and memory use; Develop compiler optimization passes and refine operator fusion; Collaborate with hardware architecture teams to accelerate Deep Learning inference computations
Seniority
Intern, New College Graduate 2027
