ChipAgents seeks an ML Systems Engineer to optimize large language model inference across multi-node clusters and to push throughput and latency bounds while reducing cost. The role is hands-on, focusing on low-level systems optimization, performance tuning, and building evaluation harnesses for production workloads.
You will work with Python and C++/CUDA, profile GPU kernels, implement inference optimizations, and collaborate with researchers to deploy new model architectures.
#J-18808-Ljbffr
We are seeking a motivated LLM Inference Systems Engineer – High-Performance & Equity to join ChipAgents in San Jose, CA, United States.
We would love to welcome a new LLM Inference Systems Engineer – High-Performance & Equity to our organisation in San Jose, CA, United States.
For the LLM Inference Systems Engineer – High-Performance & Equity position at ChipAgents, we are reviewing applications now.