Performance Engineering Architect

Hewlett Packard Enterprise; Bengaluru; On-site; INR 3,500,000 - 5,500,000; Full time

Benefits offered by this job

Health & Wellbeing

Career development programs

Unconditional inclusion

Job summary

Hewlett Packard Enterprise is seeking a Performance Expert to join the Performance Engineering team in India (Bengaluru). You will characterize and optimize the performance of AI solutions across GPUs, servers, storage, networking, and software, turning features into reproducible performance evidence for design and release readiness.

Responsibilities include designing benchmarks for GenAI workloads, analyzing LLM serving pipelines, and collaborating with product, field, and partner teams.

Qualifications

• Strong understanding of generative AI and ML performance concepts, focusing on inference performance.
• Hands-on experience deploying and benchmarking AI workloads on GPU-accelerated systems.
• Experience with inference metrics like latency, token throughput, and concurrency.
• Familiarity with LLM serving frameworks or inference runtimes such as Triton, vLLM, or Hugging Face.
• Understanding of FP formats like FP32/FP16/BF16/FP8.
• Proficiency in Python and shell scripting for automation.

Responsibilities

• Design and execute performance studies for GenAI and ML workloads.
• Characterize inference and training performance across models and deployments.
• Measure latency, throughput, and inter-token metrics at scale.
• Develop benchmark suites and automation when standard benchmarks don’t fit.
• Produce performance reports and sizing guidance for product teams.

Skills

GenAI workloads

AI benchmarking

Python

Linux

Benchmark automation

Docker

Kubernetes

NVIDIA DCGM

Prometheus

Tools

NVIDIA Perf Analyzer

Prometheus

PyNVML

VectorDBBench

Job description

This role has been designed as ‘’Onsite’ with an expectation that you will primarily work from an HPE office.

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

In the HPE Hybrid Cloud, we lead the innovation agenda and technology roadmap for all of HPE. This includes managing the design, development, and product portfolio of our next-generation cloud platform, Green Lake. Working with customers, we help them reimagine their information technology needs to deliver a simple, consumable solution that helps them drive their business results. Join us redefine what’s next for you.

What You’ll Do

We are seeking a Performance Expert to join our Performance Engineering team. The engineer will characterize and optimize the performance of AI solutions across GPUs, servers, storage, networking, system software, and AI frameworks. The role combines hands‑on benchmarking, system‑level analysis, workload optimization, automation, and collaboration with engineering, product management, field, sizing, and partner teams. The engineer will turn product features, emerging technologies, and customer questions into reproducible performance evidence that supports product design, release readiness, solution sizing, and customer decisions.

What You Need To Bring

• Design and execute performance studies for generative AI, machine learning, and other AI workloads.
• Characterize inference and training performance across models, GPUs, precision formats, deployment profiles, and scale configurations.
• Measure latency, throughput, time to first token, inter-token latency, concurrency, scaling efficiency, resource utilization, and cost/performance.
• Evaluate single-GPU, multi-GPU, and multi-node configurations.
• Analyze GPU communication, host-to-GPU bandwidth, PCIe topology, NUMA placement, memory bandwidth, storage, and networking behavior.
• Characterize LLM serving, retrieval‑augmented generation, vector database, object detection, speech, multimodal, and agentic AI workloads.
• Develop custom benchmark suites and automation when standard benchmarks do not represent the required workload.
• Identify performance bottlenecks and recommend changes to hardware configuration, BIOS settings, operating systems, drivers, runtimes, frameworks, and applications.
• Establish repeatable test methodologies, baselines, acceptance criteria, and release‑performance gates.
• Automate benchmark execution, telemetry collection, result processing, comparison, and reporting.
• Produce clear performance reports, sizing evidence, engineering recommendations, and field‑facing guidance.
• Evaluate emerging AI technologies, models, GPU platforms, storage architectures, and distributed inference techniques.
• Collaborate with solution engineering, product management, quality engineering, storage, compute, networking, solution‑sizing, field, and technology‑partner teams.

Mandatory skills: PCAI, GenAI, and AI workloads

• Strong understanding of generative AI and machine learning performance concepts, particularly inference performance.
• Hands‑on experience deploying and benchmarking AI or GenAI workloads on GPU‑accelerated systems.
• Understanding of key inference metrics like End‑to‑end latency, Time to first token, Inter‑token latency, Token throughput, Request throughput, Concurrency, Batch size, GPU utilization and memory consumption, Scaling efficiency
• Experience with LLM serving frameworks or inference runtimes such as NVIDIA NIM, vLLM, NVIDIA Triton Inference Server, TensorRT‑LLM, Hugging Face, PyTorch, or equivalent technologies.
• Understanding of model precision and quantization formats such as FP32, FP16, BF16, FP8 and NVFP4
• Working knowledge of tensor parallelism, pipeline parallelism, data parallelism, and multi‑GPU or distributed execution.
• Experience with containers and container orchestration, including Docker or Podman and Kubernetes or OpenShift.
• Strong Linux administration, troubleshooting, and performance‑analysis skills.
• Proficiency in Python and shell scripting for benchmark automation, workload orchestration, telemetry collection, and result processing.
• Experience using AI performance tools or equivalent benchmark frameworks. Relevant examples include: AIPerf, LLMPerf, NVIDIA Perf Analyzer, MLPerf, DLIO, MLPerf Storage, LMCache Bench, VectorDBBench
• Experience monitoring GPU systems using NVIDIA DCGM, nvidia‑smi, PyNVML, Prometheus, or equivalent telemetry platforms.
• Ability to correlate application‑level performance with GPU, CPU, memory, storage, and network telemetry.
• Sound understanding of statistical measurement, repeatability, run‑to‑run variation, baseline comparison, and performance‑regression analysis.
• Ability to document methodology, configurations, results, limitations, and recommendations clearly.

Domain skills: server hardware and architecture

• Strong understanding of modern server architecture, including:
• CPU sockets, cores, threads, and cache hierarchy
• NUMA architecture and processor affinity
• System memory, DIMM population, channels, bandwidth, and latency
• PCIe generations, lanes, switches, topology, and device placement
• GPU architecture, GPU memory, interconnects, and host‑to‑GPU data movement
• Local and shared storage
• Ethernet and high‑speed networking
• Hands‑on experience configuring, testing, and troubleshooting enterprise servers.
• Ability to analyze interactions among CPUs, GPUs, memory, PCIe, storage, networking, operating systems, and applications.
• Understanding of BIOS and firmware settings that affect performance, including power profiles, CPU governors, memory configuration, NUMA settings, and I/O options.
• Experience with server performance tools or equivalent utilities, such as fio, vdbench, perf/netperf, memory and GPU stream benchmarks, MLC, etc
• Ability to isolate system bottlenecks and distinguish application limitations from hardware, firmware, operating‑system, storage, or network constraints.
• Understanding of performance, price/performance, scalability, efficiency, and performance‑per‑watt considerations.
• Experience developing reproducible server configurations, test procedures, and performance baselines.
• Familiarity with enterprise hardware qualification, firmware and driver compatibility, and controlled configuration management.

Nice‑to‑have skills: virtualization

• Experience with one or more virtualization platforms:
• VMware ESXi and vSphere
• KVM
• Red Hat OpenShift Virtualization
• SUSE Harvester
• Understanding of virtual CPU, virtual NUMA, memory overcommitment, device passthrough, SR‑IOV, and GPU virtualization.
• Experience comparing virtualized and bare‑metal performance.
• Familiarity with VMware tools such as esxtop, vSAN Observer, and VMmark.
• Understanding of virtualized storage and networking performance.
• Experience diagnosing contention, noisy‑neighbor effects, resource scheduling, and virtualization overhead.
• Familiarity with Kubernetes scheduling, GPU operators, MIG, and accelerator allocation in containerized or virtualized environments.

Additional Preferred Experience

• Experience with performance benchmarks such as SPEC CPU, SPECjbb, HammerDB, TPC, SAP, or similar industry benchmarks.
• Experience with database and data‑intensive workloads, including Redis, Oracle, SQL Server, or vector databases.
• Familiarity with RAG pipelines, embedding models, reranking, KV‑cache management, and disaggregated prefill/decode architectures.
• Understanding of AI storage and data‑pipeline performance.
• Experience with observability dashboards and automated performance‑regression pipelines.
• Experience supporting benchmark audits or externally published performance results.
• Familiarity with statistical analysis and data visualization tools.
• Experience translating customer requirements into benchmark configurations and sizing recommendations.
• Prior collaboration with processor, GPU, storage, networking, or software technology partners.

Success characteristics

• Strong analytical and structured problem‑solving skills.
• Curiosity about how systems behave under realistic workloads.
• Ability to work independently in ambiguous technical areas.
• Attention to measurement accuracy, reproducibility, and configuration details.
• Ability to explain complex performance findings to engineering, product, field, and leadership audiences.
• Collaborative mindset and willingness to share tools, methodologies, and performance learnings across teams.

Accessibility

HPE is committed to creating an inclusive and accessible workplace and encourages applications from all qualified individuals, including those with disabilities.

Note: This option is reserved for applicants needing assistance/reasonable accommodation related to a disability.

What We Can Offer You

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.

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.

Let's Stay Connected

Follow @HPECareers on Instagram to see the latest on people, culture and tech at HPE.

#india

#hybridcloud

Job

Engineering

Job Level

TCP_05

EEO Statement

HPE is an Equal Employment Opportunity/ Veterans/Disabled/LGBT employer. We do not discriminate on the basis of race, gender, or any other protected category, and all decisions we make are made on the basis of qualifications, merit, and business need. Our goal is to be one global team that is representative of our customers, in an inclusive environment where we can continue to innovate and grow together.

Hewlett Packard Enterprise is EEO Protected Veteran/ Individual with Disabilities.

HPE will comply with all applicable laws related to employer use of arrest and conviction records, including laws requiring employers to consider for employment qualified applicants with criminal histories.