Raydar is recruiting for a Software Infrastructure Engineer focused on ML serving and training infrastructure in San Francisco Bay Area. You will lead end-to-end care of systems running and training custom language models, from early experiments to live production use.
The role emphasizes improving latency, throughput, and cost while ensuring reliable releases and observability. Strong low-level engineering, GPU memory, and experience with PyTorch/JAX-based serving are required.
#J-18808-Ljbffr
This posting is for the On-Site ML Infra Engineer — Fast LLM Serving & Tuning role at raydar, based in San Francisco, CA, United States.
Join us at raydar as our next On-Site ML Infra Engineer — Fast LLM Serving & Tuning in San Francisco, CA, United States.
We are currently recruiting a On-Site ML Infra Engineer — Fast LLM Serving & Tuning for our team in San Francisco, CA, United States.