Senior Deep Learning Solution Architect
Core
Designing AI computing platform architecture and solving computational challenges in LLM inference/training acceleration, network communication, and data transfer optimization.
Role type
Senior Deep Learning Solution Architect (R&D & Architecture)
Builds
Open-source inference frameworks (SGLang, vLLM), KV cache offloading frameworks (FlexKV), acceleration libraries, and performance optimization tools.
Domain
AI Computing, High-Performance Computing (HPC), Large Language Models (LLM)
Deliverable
production ML models | infrastructure
Required skills
Accelerated computing, parallel computing, heterogeneous computing, distributed training, performance optimization, data structures, computer systems fundamentals
Preferred skills
Open-source contributions, performance modeling, independent PhD-level research experience, AI coding tools
Technologies
SGLang, vLLM, FlexKV, CPU, SSD, remote storage
Responsibilities
Develop and optimize KV cache offloading frameworks for LLM workloads; Drive R&D on compute performance in distributed training; Contribute to open-source inference frameworks with feature/operator development; Study computational challenges and build example code or acceleration libraries.
Seniority
Senior, hands-on IC with R&D focus