Engineer, Staff
Core
Lead the architecture and end-to-end design of AI inference solutions on Qualcomm AI hardware, serving as the technical lead for customer engagements and driving production deployment.
Role type
Staff Engineer (AI Systems & Solutions)
Builds
AI inference programs, GenAI/LLM applications, and distributed serving architectures for datacenter customers.
Domain
Datacenter AI, Hardware Acceleration, Distributed Systems
Deliverable
production ML models
Required skills
Python, ML frameworks (PyTorch, TensorFlow), System performance profiling, Parallel computing, Model optimization, Distributed system design
Preferred skills
GenAI architectures (transformers, LLMs), Inference optimization (speculative decoding, KV cache), MLOps, Containerization (Docker, Kubernetes), Compiler optimizations, Rack-level orchestration
Technologies
PyTorch, TensorFlow, Docker, Kubernetes, Git, GitHub, C++, Java
Responsibilities
Lead architecture and design of AI inference solutions; Own customer AI engagements as technical lead; Drive development of GenAI/LLM applications; Define and execute benchmarking programs; Mentor and coach engineers; Prototype solutions for unmet technical challenges; Collaborate across cross-functional teams; Define reusable platform capabilities; Contribute to strategic decisions on model portfolio; Track advancements in AI/ML research.
Seniority
Staff, hands-on IC with leadership