LogoFresh Jobs Ahead
Hewlett Packard Enterprise
Hewlett Packard Enterprise
Sponsor pentru viza H1BHardwareInteligență artificialăÎntreprindere
Hewlett Packard Enterprise dezvoltă tehnologii pentru organizații care operează infrastructuri cloud hibride și activități bazate pe inteligență artificială. Portofoliul său include servere HPE ProLiant și soluții de calcul de înaltă performanță HPE Cray, soluții de stocare HPE Alletra, soluții de rețelistică HPE Aruba, platforme de inteligență artificială și fabrici AI gata de utilizare, precum și soluții GreenLake oferite ca serviciu. HPE oferă, de asemenea, capabilități de securitate precum Zero Trust și SASE, alături de servicii profesionale, de consultanță și de asistență care ajută organizațiile mari să își modernizeze infrastructura, să gestioneze mediile centrelor de date și să implementeze inteligența artificială la scară largă.
LinkedIn
Locurile de muncă ale companiei

Senior Inference Software Engineer at HPE Hybrid

Lead development of HPE AI Essentials’ enterprise LLM inference runtime for customer-owned infrastructure. Improve GPU-efficient serving, distributed execution, and Kubernetes orchestration.

USStatele Unite ale AmericiiCOColoradoNCCarolina de NordTXTexas
137.000 $ – 315.000 $ / an
HibridNormă întreagăSeniorLimbă Obligatorie: englezăInginer full-stackInginer software
C++GoKubernetesPython

Descriere

  • Own core components of the LLM serving deployment, including engine integration, continuous batching, KV-cache management and reuse, and quantized execution.
  • Work with inference engineering teams to reduce time to first token, inter-token latency, GPU throughput, and P95/P99 tail latency.
  • Develop and operate distributed execution features such as disaggregated prefill and decode, tensor and pipeline parallelism, and KV-cache offload across GPU memory, host memory, and RDMA-attached storage.
  • Assess emerging runtimes, quantization methods, speculative decoding, and mixture-of-experts serving, then recommend technologies for adoption.
  • Help build the orchestration layer covering model admission, GPU scheduling and partitioning, cache-aware request routing, and autoscaling.
  • Resolve customer issues end to end, determine root causes, and strengthen related systems and processes.
  • Review code and designs, mentor colleagues, and model strong engineering practices.

Cerințe

  • At least 8 years of software engineering experience.
  • One to two or more years of direct experience with LLM inference runtimes or production model serving.
  • A degree in computer science or a related discipline.
  • Familiarity with LLM inference engines such as vLLM, SGLang, TensorRT-LLM, TGI, or NVIDIA NIM, including experience modifying engine internals.
  • Strong knowledge of continuous batching, paged attention, KV-cache reuse and prefix caching, chunked prefill, quantization, and speculative decoding.
  • Working knowledge of tensor and pipeline parallelism, NCCL collective operations, GPU memory hierarchy, and interconnect behavior.
  • Advanced proficiency with Kubernetes platform architecture, including operators, custom resources, controllers, and scheduling.
  • Strong programming skills in Go and Python.
  • Ability to read, debug, and profile C++ and CUDA with tools such as Nsight.
  • Familiarity with debugging and profiling multi-tier workloads, including RAG and agent applications.
  • Excellent analytical, debugging, and problem-solving skills.
  • Preferred: Contributions to vLLM, SGLang, TensorRT-LLM, llm-d, LMCache, or KServe.
  • Preferred: Experience with disaggregated prefill and decode serving or large-scale KV-cache offload and reuse.
  • Preferred: Experience with RDMA, GPUDirect Storage, InfiniBand, or RoCE.
  • Preferred: Experience with MIG, fractional GPU allocation, and multi-tenant GPU isolation.
  • Preferred: Experience delivering software for on-premises, air-gapped, or regulated enterprise environments.

Beneficii

  • Comprehensive benefits supporting physical health, financial security, and emotional wellbeing.
  • Programs supporting personal and professional growth.
  • Flexibility for work arrangements and personal needs.
  • An inclusive workplace culture.
  • Reasonable accommodations during the application or interview process for qualified applicants with disabilities.

Locuri de muncă similare