ML Systems Engineer

Job Summary

As a full-time remote ML Systems Engineer, the successful candidate will implement new model architectures in simulation, collaborating with chip architects and SDK teams to ensure accurate execution while driving automation for model bring-up processes.

Key Responsibilities

• Implement operators, numerics, and memory layouts for new model architectures in the simulator, ensuring bit-exact execution against reference implementations
• Evaluate new architectures to identify requirements for compute, memory, and data movement prior to hardware availability
• Bring customer models up in simulation and partner with tooling engineers to automate the end-to-end model bring-up process

Required Qualifications

• 4+ years of experience as an ML systems or inference engineer
• Strong understanding of transformer internals, including attention variants, mixture-of-experts, and quantization formats
• Experience implementing or porting model inference in frameworks such as PyTorch or TensorRT-LLM
• Hands-on experience debugging numerical mismatches down to the operator level
• Strong skills in Rust or expert-level C/C++ with a willingness to work in Rust, along with strong Python skills