Senior LLM Inference Engineer — Hybrid/Remote

Hewlett Packard Enterprise; Spring (TX); Híbrido; USD 144.000 - 273.000; Jornada completa

Descripción de la vacante

Hewlett Packard Enterprise invites an experienced Senior Inference SW Engineer for a hybrid role in Spring, TX, with other US sites possible. You will help design and evolve the LLM inference runtime within AI Essentials, targeting low tail latency and high GPU utilization on customer hardware.

Responsibilities include engine integration, batching, KV cache management, and distributed execution, plus Kubernetes orchestration.

Formación

• Minimum of 8 years of experience in Software Engineering.
• 1-2+ years working directly on LLM inference runtimes or production model serving.
• Degree in Computer Science or related field.

Responsabilidades

• Design, implement, and own major components of the LLM serving deployment (engine integration, batching, KV cache management).
• Build and operate distributed execution capabilities across GPU memory, host memory, and storage.
• Collaborate with inference teams to improve time-to-first-token and tail latency; participate in code reviews and mentoring.

Conocimientos

Go

Python

Kubernetes

C++/CUDA

Distributed systems

Educación

Degree in Computer Science or related field

Herramientas

Nsight

CUDA

NCCL

Descripción del empleo

Hewlett Packard Enterprise invites an experienced Senior Inference SW Engineer for a hybrid role in Spring, TX, with other US sites possible. You will help design and evolve the LLM inference runtime within AI Essentials, targeting low tail latency and high GPU utilization on customer hardware.

Responsibilities include engine integration, batching, KV cache management, and distributed execution, plus Kubernetes orchestration.