Principal Software Engineer, Inference
for sections like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Only include sections that have real specific content. Must not repeat job title as heading. Must not include Job ID etc. Must preserve all substantive info, remove boilerplate like EEO, legal, scam warnings, navigation, cookie, etc. Also remove application instructions. Must not include filler like "commensurate with experience". Must not create Pay/Schedule/Benefits unless posting actually states them. The posting includes salary range info (Pay). It includes benefits description (Health & Wellbeing, Personal & Professional Development, Unconditional Inclusion). It includes schedule: hybrid with requirement 2 days per week from HPE office; primary work location as listed but could be any other HPE site location in US; remote work options considered. So we have schedule info. Also we have "Who We Are" which could be About the role? Actually "Who We Are" is company description; could be About the role? The instruction: use for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we can map sections: About the role (maybe "Who We Are" and job description). Responsibilities (list). Requirements (maybe Knowledge and Skills Required). Qualifications (Experience and Education). Skills (maybe Knowledge and Skills Required includes both skills and qualifications; but we can separate). Benefits (Health & Wellbeing etc). Pay (salary range). Schedule (hybrid details). We must not create sections with filler. Ensure we include all substantive info.
We must not include duplicated lines. Remove boilerplate: Accessibility, EEO, scam alert, etc. Also remove "Let's Stay Connected", social media, hashtags. Remove "Job Engineering Job Level TCP_05". Remove "Information about employee benefits offered in the US can be found at ..." maybe we keep benefits description but not link? The instruction: preserve ALL substantive information; do not invent or summarize away detail. The link to benefits is maybe substantive? It's a URL; could be considered part of benefits. But it's not essential; but we could keep as part of benefits section. However it's a link; we can include as plain text or as . The instruction didn't forbid links. It said output only HTML fragment; we can include . Probably okay.
We must not include "Accessibility" section (EEO). Must not include "Equal Employment Opportunity" etc. Must not include "Recruitment Fraud Alert". Must not include "Please click here: Equal Employment Opportunity." etc.
We must not include "Job Engineering Job Level TCP_05". That's likely metadata; drop.
We must not include "The estimated job application period closure is December 30 2027; this timeline is provided for transparency and internal planning purposes." That's maybe not substantive? It's about application period; could be considered metadata but maybe not needed. The instruction: remove application instructions. This is not exactly instruction but timeline; maybe drop as it's not substantive to role. Safer to drop.
We must not include "Note: This option is reserved for applicants needing assistance/reasonable accommodation related to a disability." That's part of Accessibility; drop.
We must not include "We strive to provide our team members and their loved ones with a comprehensive suite of benefits that supports their physical, financial and emotional wellbeing." That's benefits; keep.
We must not include "Unconditional Inclusion" etc; that's benefits? It's more culture; maybe part of Benefits or About the role. Could be included in Benefits section as part of culture benefits. But we have separate Benefits section; we can include those bullet points.
We need to use - for any list of duties/requirements/benefits. So responsibilities list, requirements list, benefits list.
We need to use
for prose.
We must not repeat job title as heading.
We must not put Job ID/requisition numbers as headings.
Ok.
Now extract content:
Who We Are: "Hewlett Packard Enterprise is the global edge-to-cloud company advancing the way people live and work. We help companies connect, protect, analyze, and act on their data and applications wherever they live, from edge to cloud, so they can turn insights into outcomes at the speed required to thrive in today’s complex world. Our culture thrives on finding new and better ways to accelerate what’s next. We know varied backgrounds are valued and succeed here. We have the flexibility to manage our work and personal needs. We make bold moves, together, and are a force for good. If you are looking to stretch and grow your career our culture will embrace you. Open up opportunities with HPE."
Job Description: "HPE's Private Cloud AI organization is seeking a Principal Software Engineer to lead the model runtime within HPE AI Essentials, the inference platform used by enterprises to operate large language models on infrastructure they own, including air-gapped and sovereign environments. The principal engineering challenge in this domain is not model deployment but sustained execution efficiency: achieving low tail latency and high GPU utilization on customer-owned hardware of varying generation and configuration. In this role you will define the architecture of that runtime – engine integration, batching, KV cache management, and distributed execution – together with the Kubernetes orchestration layer that supports it. The primary work location is as listed, but could be any other HPE site location in the US; however, remote work options will be considered."
Responsibilities: bullet list:
- Define and own the technical direction of the LLM serving deployment, including engine integration, continuous batching, KV cache management and reuse, and quantized execution
- Partner with inference performance engineering teams, with accountability for time-to-first-token, inter-token latency, throughput per GPU, and P95/P99 tail latency
- Define distributed inferencing strategy, including disaggregated prefill/decode, tensor and pipeline parallelism, KV cache offload across GPU memory, host memory, and RDMA-attached storage
- Evaluate emerging runtimes, quantization schemes, speculative decoding, and mixture-of-experts serving, and determine whether each runtime is adopted, developed in-house, or declined
- Define the orchestration layer supporting the runtime, including model admission, GPU scheduling and partitioning, cache-aware request routing, and autoscaling
- Mentor engineers, lead design and architecture reviews, and present technical direction to business unit and executive audiences
Knowledge and Skills Required: list:
- Production experience with LLM inference engines such as vLLM, SGLang, TensorRT-LLM, TGI, or NVIDIA NIM, including modification of engine internals
- Comprehensive understanding of inference internals, including continuous batching, paged attention, KV cache reuse and prefix caching, chunked prefill, quantization, and speculative decoding
- Tensor and pipeline parallelism, NCCL collective operations, and the GPU memory hierarchy and interconnect characteristics that govern them
- Expert level proficiency in Kubernetes platform architectures, including operators, custom resources, controllers, and scheduling
- Strong programming proficiency in Go and Python, with the ability to read, debug, and profile C++/CUDA using tools such as Nsight
- Experience with debugging/profiling multi-tier application workloads such as RAG, Agents, etc
- Excellent analytical, debugging, and problem-solving abilities
Preferred: list:
- Upstream contribution to vLLM, SGLang, TensorRT-LLM, LLM-D, LMCache, or KServe
- Disaggregated prefill/decode serving, or KV cache offload and reuse at scale
- RDMA, GPUDirect Storage, InfiniBand, or RoCE
- MIG, fractional GPU allocation, and multi-tenant GPU isolation
- On-premises, air-gapped, or regulated enterprise software delivery
Experience and Education: "Minimum of 12 years of experience in Software Engineering, including +1 years working directly on LLM inference runtimes or production model serving Degree in Computer Science or related field"
Benefits: sections:
Health & Wellbeing: "We strive to provide our team members and their loved ones with a comprehensive suite of benefits that supports their physical, financial and emotional wellbeing."
Personal & Professional Development: "We also invest in your career because the better you are, the better we all are. We have specific programs catered to helping you reach any career goals you have — whether you want to become a knowledge expert in your field or apply your skills to another division."
Unconditional Inclusion: "We are unconditionally inclusive in the way we work and celebrate individual uniqueness. We know varied backgrounds are valued and succeed here. We have the flexibility to manage our work and personal needs. We make bold moves, together, and are a force for good."
Maybe also "Let's Stay Connected" etc drop.
Pay: salary range: "The expected salary/wage range for this position is provided below. Actual offer may vary from this range based upon geographic location, work experience, education/training, and/or skill level. – United States of America: Annual Salary USD 160,000 - 303,000 in Colorado // 152,000 - 349,000 in North Carolina & Texas The listed salary range reflects base salary. Variable incentives may also be offered."
Schedule: hybrid: "This role has been designed as 'Hybrid' with a requirement that you will work on average 2 days per week from an HPE office. The primary work location is as listed, but could be any other HPE site location in the US; however, remote work options will be considered."
We also have "Open up opportunities with HPE." maybe part of About the role.
Now produce HTML.
Structure:
About the role
Who We Are ... Job Description ...
But we need to avoid duplication: maybe combine Who We Are and Job Description into About the role paragraph.
We'll put two paragraphs: one for Who We Are, one for Job Description.
Then Responsibilities
...
Requirements
maybe combine Knowledge and Skills Required + Preferred? But we have separate sections: Requirements (maybe Knowledge and Skills Required) and Qualifications (Experience and Education). Skills could be part of Requirements. But we can follow instruction: use headings as appropriate. We'll include Requirements (Knowledge and Skills Required) and Qualifications (Experience and Education). Also maybe Skills separate? But we can merge.
We'll do:
Requirements
... (Knowledge and Skills Required)
Preferred Skills
... (Preferred)
but instruction only gave example headings; we can use Skills heading for preferred? Might be okay. But we can also include under Requirements.
Better to follow: Requirements (mandatory) and Qualifications (experience/education). Skills maybe part of Requirements. We'll not create extra Skills section unless we have distinct skills list; we have both mandatory and preferred skills. Could combine.
But we need to avoid thin sections. Let's make:
Requirements
mandatory
Preferred Qualifications
preferred
Experience and Education
...
But we already have Qualifications heading example; we can use Qualifications for experience/education.
Thus:
Requirements
mandatory
Qualifications
Minimum of 12 years ... Degree in Computer Science or related field
Preferred Skills
preferred
But we might combine Preferred Skills into Requirements? Might be okay.
Benefits: Benefits
... each benefit as
Pay: Pay
salary range text
Schedule: Schedule
hybrid text
We must not include filler like "commensurate with experience". Not present.
Now ensure we
- for any list of duties/requirements/benefits. So responsibilities list, requirements list, benefits list.
We need to use
for prose. We must not repeat job title as heading. We must not put Job ID/requisition numbers as headings. Ok. Now extract content: Who We Are: "Hewlett Packard Enterprise is the global edge-to-cloud company advancing the way people live and work. We help companies connect, protect, analyze, and act on their data and applications wherever they live, from edge to cloud, so they can turn insights into outcomes at the speed required to thrive in today’s complex world. Our culture thrives on finding new and better ways to accelerate what’s next. We know varied backgrounds are valued and succeed here. We have the flexibility to manage our work and personal needs. We make bold moves, together, and are a force for good. If you are looking to stretch and grow your career our culture will embrace you. Open up opportunities with HPE." Job Description: "HPE's Private Cloud AI organization is seeking a Principal Software Engineer to lead the model runtime within HPE AI Essentials, the inference platform used by enterprises to operate large language models on infrastructure they own, including air-gapped and sovereign environments. The principal engineering challenge in this domain is not model deployment but sustained execution efficiency: achieving low tail latency and high GPU utilization on customer-owned hardware of varying generation and configuration. In this role you will define the architecture of that runtime – engine integration, batching, KV cache management, and distributed execution – together with the Kubernetes orchestration layer that supports it. The primary work location is as listed, but could be any other HPE site location in the US; however, remote work options will be considered." Responsibilities: bullet list: - Define and own the technical direction of the LLM serving deployment, including engine integration, continuous batching, KV cache management and reuse, and quantized execution - Partner with inference performance engineering teams, with accountability for time-to-first-token, inter-token latency, throughput per GPU, and P95/P99 tail latency - Define distributed inferencing strategy, including disaggregated prefill/decode, tensor and pipeline parallelism, KV cache offload across GPU memory, host memory, and RDMA-attached storage - Evaluate emerging runtimes, quantization schemes, speculative decoding, and mixture-of-experts serving, and determine whether each runtime is adopted, developed in-house, or declined - Define the orchestration layer supporting the runtime, including model admission, GPU scheduling and partitioning, cache-aware request routing, and autoscaling - Mentor engineers, lead design and architecture reviews, and present technical direction to business unit and executive audiences Knowledge and Skills Required: list: - Production experience with LLM inference engines such as vLLM, SGLang, TensorRT-LLM, TGI, or NVIDIA NIM, including modification of engine internals - Comprehensive understanding of inference internals, including continuous batching, paged attention, KV cache reuse and prefix caching, chunked prefill, quantization, and speculative decoding - Tensor and pipeline parallelism, NCCL collective operations, and the GPU memory hierarchy and interconnect characteristics that govern them - Expert level proficiency in Kubernetes platform architectures, including operators, custom resources, controllers, and scheduling - Strong programming proficiency in Go and Python, with the ability to read, debug, and profile C++/CUDA using tools such as Nsight - Experience with debugging/profiling multi-tier application workloads such as RAG, Agents, etc - Excellent analytical, debugging, and problem-solving abilities Preferred: list: - Upstream contribution to vLLM, SGLang, TensorRT-LLM, LLM-D, LMCache, or KServe - Disaggregated prefill/decode serving, or KV cache offload and reuse at scale - RDMA, GPUDirect Storage, InfiniBand, or RoCE - MIG, fractional GPU allocation, and multi-tenant GPU isolation - On-premises, air-gapped, or regulated enterprise software delivery Experience and Education: "Minimum of 12 years of experience in Software Engineering, including +1 years working directly on LLM inference runtimes or production model serving Degree in Computer Science or related field" Benefits: sections: Health & Wellbeing: "We strive to provide our team members and their loved ones with a comprehensive suite of benefits that supports their physical, financial and emotional wellbeing." Personal & Professional Development: "We also invest in your career because the better you are, the better we all are. We have specific programs catered to helping you reach any career goals you have — whether you want to become a knowledge expert in your field or apply your skills to another division." Unconditional Inclusion: "We are unconditionally inclusive in the way we work and celebrate individual uniqueness. We know varied backgrounds are valued and succeed here. We have the flexibility to manage our work and personal needs. We make bold moves, together, and are a force for good." Maybe also "Let's Stay Connected" etc drop. Pay: salary range: "The expected salary/wage range for this position is provided below. Actual offer may vary from this range based upon geographic location, work experience, education/training, and/or skill level. – United States of America: Annual Salary USD 160,000 - 303,000 in Colorado // 152,000 - 349,000 in North Carolina & Texas The listed salary range reflects base salary. Variable incentives may also be offered." Schedule: hybrid: "This role has been designed as 'Hybrid' with a requirement that you will work on average 2 days per week from an HPE office. The primary work location is as listed, but could be any other HPE site location in the US; however, remote work options will be considered." We also have "Open up opportunities with HPE." maybe part of About the role. Now produce HTML. Structure:
About the role
Who We Are ... Job Description ...
But we need to avoid duplication: maybe combine Who We Are and Job Description into About the role paragraph. We'll put two paragraphs: one for Who We Are, one for Job Description. ThenResponsibilities
- ...
Requirements
maybe combine Knowledge and Skills Required + Preferred? But we have separate sections: Requirements (maybe Knowledge and Skills Required) and Qualifications (Experience and Education). Skills could be part of Requirements. But we can follow instruction: use headings as appropriate. We'll include Requirements (Knowledge and Skills Required) and Qualifications (Experience and Education). Also maybe Skills separate? But we can merge. We'll do:Requirements
- ... (Knowledge and Skills Required)
Preferred Skills
- ... (Preferred)
Requirements
- mandatory
Preferred Qualifications
- preferred
Experience and Education
...
But we already have Qualifications heading example; we can use Qualifications for experience/education. Thus:Requirements
- mandatory
Qualifications
Minimum of 12 years ... Degree in Computer Science or related field
Preferred Skills
- preferred
Benefits
- ... each benefit as
Pay
salary range text
Schedule:Schedule
hybrid text
We must not include filler like "commensurate with experience". Not present. Now ensure we