Software QA Engineer Data Analysis and Test Operation
FuriosaAI is a South Korean AI semiconductor company building energy-efficient inference accelerators, servers, and software for enterprise and cloud AI deployments.
Funding history
Investors
About FuriosaAI
FuriosaAI develops the RNGD AI inference accelerator and NXT RNGD Server, alongside a software toolchain for compiling, optimizing, and deploying LLM and agentic-AI workloads.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will plan and operate software evaluations for NPU products and supporting software across boards, servers, operating systems, and software versions. You will analyze functional, performance, power, temperature, and log data; identify regressions and abnormal variation; reproduce defects; collaborate with engineers on fixes; and document quality status for release reviews.
Requirements
- Experience in software QA or test design and execution.
- Ability to translate requirements into testable scenarios and acceptance criteria.
- Ability to prioritize test scope based on normal, exception, boundary, and change-impact conditions.
- Ability to use basic Linux commands and provided test tools to inspect logs, processes, and device status.
- Ability to compare and organize results using tables, CSV files, and dashboards.
- Ability to interpret distributions and deviations in basic measurements.
- Ability to read and make simple changes to existing Python or shell scripts.
- Understanding of relationships among NPU boards, server environments, firmware, drivers, and SDKs.
- Ability to clearly document observed facts, root-cause hypotheses, reproduction conditions, expected and actual results, and analysis evidence.
Responsibilities
- Define evaluation scope, priorities, test conditions, procedures, expected results, and acceptance criteria.
- Operate tests using defined board, server, operating system, kernel, and software-version conditions.
- Manage test schedules, coverage, progress, unverified items, and controlled retests.
- Analyze functional, benchmark, power, temperature, and system-log data.
- Compare repeated measurements and prior-version results to identify regressions and abnormal variation.
- Reproduce defects and distinguish product defects from server-environment or test-program issues.
- Provide logs, versions, device information, expected results, actual results, and analysis evidence to engineers.
- Revalidate fixes and perform related regression testing.
- Report evaluation results, defects, impact, decision rationale, and unverified risks for release reviews.
- Document tool-improvement requirements from recurring analysis and operational issues.