Engineer, Principal
Core
Lead high-performing teams to develop and optimize machine learning frameworks and deep learning models for Qualcomm's AI 100, spanning data center, edge, and automotive markets.
Role type
Principal Machine Learning Software Engineer (Framework & Optimization)
Builds
Deep learning framework extensions, inference accelerator abstraction layers, and optimized ML pipelines for Qualcomm AI 100.
Domain
Semiconductor / Machine Learning / High-Performance Computing
Deliverable
production ML models
Required skills
Machine Learning framework development, Deep Learning optimization, C++ (advanced features), Python, Linear Algebra, Mathematical modeling, System design, Open-source development, Graph compiler integration, Multi-threaded high-performance code, SIMD, CUDA/CUDNN, MLIR, Auto-code generation, Large-scale heterogeneous cluster workloads
Preferred skills
LLMs, NLP, Vision, Audio, Recommendation systems, PyTorch/TensorFlow internals, Software profiling, Tiling and scheduling of ML operators, vLLM, Triton, ExecuTorch, Inductor, TorchDynamo
Technologies
Qualcomm AI 100, C++, Python, PyTorch, TensorFlow, CUDA, CUDNN, MLIR, vLLM, Triton, ExecuTorch, Inductor, TorchDynamo
Responsibilities
Analyze software requirements and determine design feasibility for Qualcomm SOCs; Lead high-performing teams towards system design and deliverables; Improve and optimize key Deep Learning models on Qualcomm AI 100; Build deep learning framework extensions for upstream open-source repositories; Collaborate to analyze and optimize training and inference for deep learning; Build software tools and ecosystem around AI SW Stack; Work on vLLM, Triton, ExecuTorch, Inductor, TorchDynamo to build abstraction layers for inference accelerator; Optimize workloads for both scale-up and scale-out systems; Optimize the entire deep learning pipeline including graph compiler integration.
Seniority
Principal, hands-on IC with team leadership
