F

FuriosaAI

Power-efficient AI inference accelerator chips

Software QA Engineer - Data Analysis, Test Operation

Manual & Functional QAConfirmed live in the last 24 hours
Full-timeSeoul, South KoreaNo salary listedIn-person

About the Job

Requirements

  • Experience in software quality assurance or test design and execution, with the ability to turn requirements into verifiable scenarios and acceptance criteria.
  • Ability to define test scope and priorities while accounting for normal, exception, and boundary conditions and the impact of changes.
  • Ability to run evaluations using basic Linux commands and provided test tools, and inspect logs, processes, and device status.
  • Ability to compare and organize results using tables, CSV files, and existing dashboards, and interpret basic measurement distributions and deviations.
  • Ability to read and run existing Python or Shell scripts and make simple changes for execution conditions or data preparation.
  • Basic understanding of relationships among NPU boards, server environments, firmware, drivers, and SDKs, and ability to account for them in test conditions and result interpretation.
  • Ability to distinguish observed facts from causal hypotheses and clearly document reproduction conditions, expected and actual results, and analysis evidence.

Responsibilities

  • Review product requirements, developer guides, release changes, and existing defects to set evaluation scope and priorities; distinguish normal, exception, and boundary conditions, compatibility, and regression items; and document test objectives, prerequisites, procedures, expected results, and pass/fail criteria.
  • When test programs need additions or changes, provide software engineers with input conditions, required result data, and reproduction scenarios.
  • Verify board, server, operating system, kernel, and software versions, then execute tests using provided frameworks and tools.
  • Identify interruptions, missing logs, and environment configuration errors during testing, and distinguish valid test results from those requiring reruns.
  • Manage evaluation schedules, coverage, progress, and untested items, and perform retesting under controlled conditions.
  • Interpret functional results, benchmark performance, power, temperature, and system logs together.
  • Compare repeated measurements under identical conditions with results from previous versions to distinguish normal variation, performance regressions, server-specific differences, and abnormal board deviations.
  • Use existing dashboards and analysis tools, supplementing them where needed with CSV organization, simple queries, or scripts; account for how execution-condition differences affect interpretation.
  • Determine the conditions and reproducibility of abnormal behavior, and investigate whether it may originate in the product, server environment, or test program.
  • Provide development teams with relevant logs, versions, device information, expected and actual results, and other defect details.
  • After fixes, rerun verification under the same conditions and perform related regression tests; confirm resolution and identify residual impacts.
  • Summarize evaluation results, major defects, impact scope, decision rationale, and unverified risks for release reviews.
  • Document recurring analysis and operational difficulties as specific tool-improvement requirements.
  • Produce evaluation plans and test-case documents, execution-condition and result records, defect-analysis materials, and quality-verification reports.

Desired Qualifications

  • Experience with software quality assurance for AI accelerators such as NPUs or GPUs, SDKs, or software integrated with hardware and drivers.
  • Experience with LLM model serving, vLLM, and performance benchmarking tools.
  • Experience analyzing performance regressions across versions, board-to-board variation, power efficiency, or long-duration stability.
  • Experience with basic SQL queries, statistical comparisons, or tools such as Grafana, Superset, or Metabase.
  • Experience analyzing how PCIe, NUMA, temperature, clock speed, and throttling affect performance.
  • Experience improving verification scope based on customer use cases or operating release verification.

About the Company

FuriosaAI

Power-efficient AI inference accelerator chips

FuriosaAI develops AI accelerators for data centers. Its flagship RNGD chip is a power-efficient accelerator designed to boost performance per watt for running large language models and other demanding AI workloads. The hardware is configurable with multiple processing elements to fit different workloads, and it is paired with advanced compiler technology and profiling tools to identify bottlenecks and optimize efficiency. This combination of flexible hardware and software optimization differentiates FuriosaAI from competitors, focusing on maximizing performance while keeping energy use low. The company targets data centers and enterprises that need high-performance, energy-efficient AI solutions, and aims to make AI computing more sustainable and scalable by selling its chips and related software tools and pursuing long-term contracts with large-scale customers.

Company size
201-500
Company stage
Series D
Total funding
$887.5M
Headquarters
Seoul, South Korea
Founded
2017

Recently Posted Jobs

Explore more opportunities at FuriosaAI

See more jobs