Principal AI/ML System Software Engineer
Core
Building and scaling the next-generation AI deployment software stack and deployment infrastructure for an AI compute engine.
Role type
Principal System Software Engineer (AI Inference Execution)
Builds
Production AI inference software and deployment infrastructure
Domain
AI compute hardware/software co-design and inference execution
Deliverable
production ML models
Required skills
C/C++/Python development, Linux environment, distributed high-performance software design, computer architecture, data structures, machine learning fundamentals
Preferred skills
Inference servers/model serving frameworks, deep learning frameworks, deep learning runtimes, distributed systems collectives, software testing fundamentals, MLOps tools, Kubernetes, Ray, startup/incubation experience, cloud provider or AI compute company experience
Technologies
TensorRT-LLM, vLLM, SGLang, PyTorch, TensorFlow, ONNX Runtime, TensorRT, NCCL, OpenMPI, Kubernetes, Ray
Responsibilities
Develop, enhance, and maintain next-generation AI deployment software; work with system software experts to build deployment infrastructure; collaborate with ML, compilers, and hardware experts; build and scale software deliverables within tight development windows
Seniority
Principal, hands-on IC with leadership
