Senior Principal ML Inference Engine Architect

Ampere Computing LLC; Portland (OR); Presencial; USD 226.000 - 339.000; Jornada completa

Descripción de la vacante

Ampere Computing LLC in Portland, OR, seeks a Sr. Principal Machine Learning Software Engineer to lead the architecture and development of a high-performance AI inference-serving engine for Ampere accelerators.

You will work across model serving, frameworks, compilers, runtimes, and optimized kernels to enable efficient AI workloads. This hands-on leadership role requires solving complex systems challenges, mentoring engineers, and driving hardware/software co-design.

Formación

• 12+ years of relevant experience; or Master’s with 8+ years; or Ph.D. with 5+ years.
• Experience developing or optimizing production inference runtimes, serving engines, deployment toolkits, or high‑performance AI systems.
• Experience with technologies such as vLLM, llama.cpp, TensorRT/TensorRT-LLM, ONNX Runtime, OpenVINO, Triton, TVM, XLA, MLIR, or equivalents.

Responsabilidades

• Architect and build an inference-serving engine for state-of-the-art models on Ampere accelerators.
• Drive end-to-end serving performance: throughput, latency, tail latency, memory efficiency, scalability, cost per inference.
• Collaborate across model-serving, framework, compiler, runtime, kernel, and hardware teams to deliver a cohesive AI stack.
• Optimize model execution through graph compilation, operator fusion, precision optimization, and hardware-specific strategies.
• Mentor engineers and lead cross-functional technical initiatives.
• Partner with product, field, and customer teams to prioritize capabilities and deliver production-ready AI solutions.

Conocimientos

C++ expert

Concurrent programming

Performance optimization

AI inference

Cross-functional leadership

Educación

Bachelor’s +12+ yrs

Master’s +8+ yrs

PhD +5+ yrs

Herramientas

vLLM

llama.cpp

TensorRT

ONNX Runtime

TVM

CUDA

Descripción del empleo

Ampere Computing LLC in Portland, OR, seeks a Sr. Principal Machine Learning Software Engineer to lead the architecture and development of a high-performance AI inference-serving engine for Ampere accelerators.

You will work across model serving, frameworks, compilers, runtimes, and optimized kernels to enable efficient AI workloads. This hands-on leadership role requires solving complex systems challenges, mentoring engineers, and driving hardware/software co-design.