Staff ML Engineer
Core
Optimize training and inference performance across GPU and AI-accelerator infrastructure, design and productionize ML models (deep learning, LLMs, CV, recommendation systems), and develop low-level software for NPU cores and embedded environments.
Role type
Staff ML Engineer (AI Infrastructure & Hardware Systems)
Builds
Production ML models, optimized inference engines, NPU cores, and AI-assisted verification harnesses for hardware.
Domain
Semiconductor hardware, AI infrastructure, embedded systems, cybersecurity.
Deliverable
production ML models
Required skills
GPU cluster management, distributed training, inference-serving optimization, MLOps pipelines, model quantization, NPU/AI accelerator expertise, systems-level software development, embedded Linux/RTOS programming, RTL/DV verification, hardware security analysis.
Preferred skills
PhD in relevant field, experience with CoralNPU or similar NPUs, deep expertise in firmware development.
Technologies
Zephyr, BMC firmware, embedded Linux, RTOS, GPU clusters, CoralNPU.
Responsibilities
Harden and extend NPU cores into production silicon; Build automated test and verification harnesses for AI-assisted RTL/DV; Apply ML to log and intrusion analysis for security; Collaborate with RTL, hardware, firmware, and QA teams to ship AI features. (via careerplan.io/jobs/22495-staff-ml-engineer-at-axiado)
Seniority
Senior, hands-on IC
