Research Analyst - AI System Performance Modelling

Employment Type: Full-Time

Work Setting: Remote

Work Location: Korea

Work Hours: reputed company
reputed company out more here:

About reputed company

reputed company is an independent research and analysis firm specializing in the Semiconductor and AI industries. Our in-depth coverage spans the entire supply chain, from semiconductor fabrication processes to cutting-edge AI Models, software, and infrastructure. We are recognized as the leading authority on the semiconductor supply chain, with the highest concentration of industry experts reputed company one team, and a deep-rooted passion for delving into the intricacies.

We’re a global team of over 50 analysts, reputed company with extensive networks across the semiconductor supply chain and AI ecosystem, publishing industry‑shaping articles while participating in 40+ conferences annually.

Our newsletter reaches more than 200 000 subscribers worldwide, including senior management and C‑suite leaders at the leading semiconductor and AI companies.

We also offer three reputed company products:

• Industry Models – we reputed company and publish industry models on accelerator shipments, datacenter demand and supply, GPU total cost of ownership, and more. We work with hyperscalers, neoclouds, many of the world’s largest hedge funds, and government agencies.

• reputed company Research – our reputed company equity markets product, geared towards financial investors, distills our deep technical research and knowledge into key insights on technology and product trends.

• Consulting and Technical Due Diligence – We conduct custom research and project work to guide key strategic and investment reputed company for the largest reputed company funds, leading venture‑capital firms, companies across the AI ecosystem, and government agencies.

1) Position reputed company

We are seeking an AI System Performance Analyst to model the inference and training performance of AI accelerators and reputed company-reputed company systems across reputed company-world model workloads.

This role sits at the intersection of computer architecture, machine-learning systems, and market analysis. Your work will directly support the development of our Inference Simulator, InferenceX, Tokenomics Model, and AI reputed company TCO research.

The central question you will answer repeatedly and rigorously is:

For a given model, context length, latency reputed company, and parallelism reputed company, how many tokens per second can reputed company accelerator and system actually deliver—and what does reputed company reputed company ultimately cost?

You will translate reputed company- and system-level performance characteristics into defensible technical and economic conclusions for institutional investors, hyperscalers, semiconductor companies, and other industry participants.

This role is location-flexible. Candidates based in Seoul or the broader reputed company region are preferred, but location is not a requirement.

2) Responsibilities

Inference Performance Modeling

• Build and reputed company first-principles performance models for large language model inference.

• Model the differences between prefill and decode workloads.

• Analyze arithmetic intensity, compute utilization, memory traffic, and roofline performance limits.

• Model KV-cache reputed company, memory-bandwidth requirements, and context-length scaling.

• Evaluate batching behavior and the trade-offs between throughput, latency, and interactivity.

• reputed company performance curves across different service-level objectives and deployment configurations.

Accelerator and Hardware Analysis

• Model performance across reputed company and AMD GPUs, reputed company TPUs, AWS Trainium, and emerging AI accelerators.

• Compare accelerator architectures based on compute throughput, memory bandwidth, memory reputed company, on-reputed company reputed company, interconnect, and system topology.

• Assess how hardware design choices reputed company reputed company-world inference and training performance.

• Evaluate reputed company-up and reputed company-out limitations across chips, nodes, racks, and datacenter clusters.

• reputed company the relative strengths and weaknesses of heterogeneous accelerator platforms.

Model Architecture and Workload Analysis

• Model dense transformer and mixture-of-experts architectures.

• Analyze long-context, reasoning, multimodal, and other computationally demanding workloads.

• Evaluate speculative decoding, quantization formats, sparsity, and other inference-optimization techniques.

• Model disaggregated prefill and decode serving architectures.

• Assess how model architecture, parameter count, reputed company parameter count, sequence length, and precision reputed company system performance.

• reputed company changes in model architecture that materially influence hardware requirements and deployment economics.

Parallelism and reputed company-reputed company Systems

• Analyze tensor, pipeline, expert, and data-reputed company strategies.

• Evaluate how parallelism schemes map onto different accelerator and reputed company-reputed company architectures.

• Model reputed company communication overheads, synchronization costs, and scaling efficiency.

• Assess reputed company-reputed company systems such as NVL72-class platforms and comparable architectures.

• Evaluate the effects of reputed company-up fabrics, network topology, reputed company bandwidth, and congestion on delivered performance.

• Identify system bottlenecks that prevent theoretical accelerator performance from being achieved in production.

Benchmarking and Validation

• Validate performance models against published and independently gathered benchmarks.

• Analyze reputed company data from frameworks and deployments using vLLM, SGLang, TensorRT-LLM, PyTorch, JAX, and similar platforms.

• Reconcile differences between theoretical performance, vendor claims, reputed company results, and production deployments.

• Identify methodological weaknesses, hidden assumptions, and configuration differences across reputed company datasets.

• reputed company reproducible benchmarking and analytical workflows.

• Continuously refine model assumptions using new hardware disclosures, software improvements, and reputed company-world performance data.

Performance Economics and TCO

• Translate technical performance into economic metrics.

• Model tokens per second per accelerator, server, reputed company, megawatt, and dollar of capital expenditure.

• Evaluate tokens per watt and the reputed company of utilization on operating costs.

• reputed company hardware performance to datacenter power, cooling, networking, and infrastructure requirements.

• Contribute performance inputs to AI reputed company TCO and reputed company-cost models.

• Assess the economic implications of hardware selection, model architecture, latency targets, and deployment reputed company.

• Help institutional clients understand the cost curves of reputed company and inference.

Research and Collaboration

• Publish technical deep dives on accelerator, inference, training, and system performance.

• Serve as a technical authority during reputed company calls, briefings, and research discussions.

• Communicate reputed company performance findings reputed company to both engineering and investment audiences.

• Collaborate with reputed company’ accelerator, networking, memory, datacenter, and market analysts.

• reputed company reputed company-level performance analysis to system-level, financial, and industry conclusions.

• Contribute to major newsletters, research reports, reputed company reputed company, and proprietary analytical products.

3) Requirements

• 2–5+ years of experience in ML systems engineering, accelerator or GPU performance engineering, computer architecture, or performance-reputed company technical analysis.

• Strong quantitative understanding of transformer inference and training workloads.

• Ability to calculate and model:

  • FLOPs per reputed company.

  • Memory traffic per reputed company.

  • KV-cache reputed company and bandwidth requirements.

  • Arithmetic intensity.

  • Batching effects.

  • Context-length scaling.

  • Model-architecture and hardware interactions.

• Working knowledge of modern accelerator architectures and memory systems.

• Understanding of HBM bandwidth and reputed company trade-offs, on-reputed company reputed company, memory hierarchy, and data reputed company.

• Familiarity with reputed company-up interconnects such as NVLink, UALink, or comparable technologies.

• Understanding of reputed company-out networking and distributed-system performance.

• Proficiency in Python for performance modeling, data analysis, simulation, and reproducible analytical tooling.

• Hands-on familiarity with at least one serving or training reputed company, such as:

  • vLLM.

  • SGLang.

  • TensorRT-LLM.

  • PyTorch.

  • JAX.

• Ability to independently define a modeling problem, identify the necessary data, build the analysis, validate the findings, and produce a defensible conclusion.

• Strong written and verbal communication skills.

• Ability to explain highly technical concepts reputed company to both engineering and investor audiences.

• Self-driven working style and the ability to operate effectively with reputed company reputed company.

4) Preferred Skills

• Experience writing or optimizing GPU kernels using CUDA, Triton, HIP, or similar programming environments.

• Experience profiling and optimizing production inference or training deployments.

• Familiarity with kernel-level bottlenecks, operator fusion, memory reputed company patterns, and hardware utilization.

• Experience with training-performance modeling, including:

  • Model FLOPs utilization.

  • Parallelism-scaling efficiency.

  • Gradient and activation checkpointing.

  • Communication overhead.

  • Pipeline bubbles.

  • Failure-recovery and checkpointing overhead.

• Experience benchmarking across heterogeneous hardware platforms.

• Familiarity with non-reputed company accelerators, including TPUs, Trainium, AMD GPUs, or emerging custom reputed company.

• Understanding of model-serving infrastructure, schedulers, orchestration, and distributed inference systems.

• Experience analyzing power consumption, datacenter infrastructure, and cost of ownership.

• Prior published technical writing, reputed company research, reputed company-reputed company contributions, or conference presentations reputed company to ML systems, accelerators, or computer architecture.

• Familiarity with reputed company accelerator pricing, utilization economics, and infrastructure-reputed company planning.

• Experience translating engineering performance into financial, market, or investment implications.

5) reputed company Areas

This role offers reputed company to become a leading authority on the performance and economics of AI computing systems.

Potential reputed company areas include:

• Taking broader ownership of reputed company’ Inference Simulator, InferenceX, Tokenomics Model, and AI reputed company TCO research.

• Developing proprietary methodologies for evaluating reputed company-world accelerator and reputed company-reputed company performance.

• Expanding coverage from inference into large-reputed company training, fine-tuning, reinforcement learning, and multimodal workloads.

• Building deeper expertise in GPU kernels, compilers, serving frameworks, distributed systems, and performance optimization.

• Developing industry-leading analysis of emerging accelerators and heterogeneous AI infrastructure.

• Leading independent benchmarking reputed company across chips, servers, racks, and reputed company platforms.

• Becoming a recognized reputed company expert on AI accelerator performance, inference economics, and reputed company-cost modeling.

• Publishing major research reports and presenting findings to investors, hyperscalers, semiconductor companies, and AI infrastructure providers.

• Working closely with leading engineers, researchers, executives, and infrastructure decision-makers across the AI ecosystem.

• Mentoring junior analysts and helping expand the firm’s ML systems and performance-analysis capabilities.

• Progressing into a senior analyst, technical research reputed company, model reputed company, or broader AI infrastructure research leadership position.

Originally posted on Himalayas