Senior LLM Inference Engineer - Hybrid

Hewlett Packard Enterprise Development LP; Spring (TX); Híbrido; USD 140.000 - 315.000; Jornada completa

Descripción de la vacante

Hewlett Packard Enterprise is seeking a Senior Software Engineer to build and evolve the model runtime within HPE AI Essentials, focusing on low tail latency and high GPU utilization on customer-owned hardware. The role is hybrid with 2 days per week in an HPE office and flexibility for other sites in the US.

You will design major LLM deployment components, collaborate with inference teams, and help scale distributed execution with quantization and caching strategies.

Formación

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

Responsabilidades

• Design and own major components of the LLM serving deployment.
• Improve time-to-first-token and tail latency across GPUs.
• Develop distributed execution capabilities across memory hierarchies.
• Evaluate runtimes and quantization schemes and recommend adoption.
• Support runtime orchestration, GPU scheduling, and autoscaling.
• Troubleshoot customer issues end-to-end and mentor teammates.

Conocimientos

LLM inference

Inference internals

GPU memory hierarchy

NCCL operations

Go programming

Python programming

Code profiling

Multi-tier debugging

Problem solving

Educación

Bachelor's degree in Computer Science or related field

Herramientas

Kubernetes

Nsight

C++/CUDA

Descripción del empleo

Hewlett Packard Enterprise is seeking a Senior Software Engineer to build and evolve the model runtime within HPE AI Essentials, focusing on low tail latency and high GPU utilization on customer-owned hardware. The role is hybrid with 2 days per week in an HPE office and flexibility for other sites in the US.

You will design major LLM deployment components, collaborate with inference teams, and help scale distributed execution with quantization and caching strategies.