Member of Technical Staff - Inference Systems

What you'll do

• Design benchmark suites for inference performance, model quality, and knowledge evaluation across hardware targets.
• Evaluate partner solutions against benchmarks, identify gaps, and communicate findings.
• Port models across runtimes and frameworks, verify correctness, and extend the inference engine layer.

What they ask for

• Hands-on experience modifying internals of at least one inference framework, such as llama.cpp, ONNX Runtime, or MLX.
• Experience designing and building benchmarking pipelines, including methodology, validation, and reproducibility.
• Strong C++ and Python in performance-sensitive contexts.
• Understanding of inference fundamentals, including quantization, decoding strategies, and memory layout.

Nice to have

• Experience porting models across runtimes and verifying numerical correctness; technical validation or evaluation with external partners or clients.
• Familiarity with edge inference targets and their constraints.

Tools

llama.cpp, ONNX, MLX, ONNX Runtime, C++, Python

AI focus

Inference systems, model porting, and benchmarking AI model performance and quality.