AI Engineer

What you'll do

• Build, tune, and maintain inference-serving components and frameworks for production models.
• Profile GPU workloads, diagnose bottlenecks, and implement and benchmark inference optimizations.
• Partner with researchers to productionize new architectures and support deployed services.

What they ask for

• Degree in Computer Science, Computer Engineering, or a related field, or equivalent practical experience.
• Hands-on experience serving and modifying at least one inference framework.
• Working knowledge of GPU-based LLM inference and experience profiling, debugging, and shipping a measured GPU performance optimization.
• Strong Python and C++ programming skills, plus depth in at least one area such as speculative decoding, batching, KV cache design, quantization, or distributed serving.

Nice to have

• Merged contributions to vLLM, SGLang, TensorRT-LLM, PyTorch, or similar projects; CUDA, Triton, or CUTLASS kernel development.
• Experience with MoE or 100B+ parameter models, multi-node inference, or graduate study/research in ML systems, compilers, or high-performance computing.

Pay

$137,700.00 - $275,400.00 (salary range or on-target earnings; base salary and/or OTE not specified)

Tools

Python, C++, vLLM, SGLang, TensorRT-LLM, ONNX Runtime, Nsight Systems, CUDA

AI focus

Production inference for transformer and multimodal models, including performance optimization, quantization, GPU profiling, and bringing new model architectures into production.