Production Operation Engineer
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 support NPU production operations by maintaining test environments and production programs. You will automate recurring work, monitor production data and failures, deploy program changes, troubleshoot operational issues, and support manufacturing partners with clear procedures and reports.
Requirements
- 3 to 5 years of experience in system operations, data analysis, or process improvement.
- Understanding of production or test flows and ability to operate existing systems reliably and analyze problems.
- Ability to write, modify, and maintain production-operation programs and scripts using Python or Bash.
- Ability to investigate files, logs, processes, execution status, and test errors in Linux.
- Ability to collect and validate data and explain causes and improvements using yield, defect-rate, and test-result changes.
- Ability to manage program deployment history and execution conditions and write operating and incident-response guides.
- Ability to communicate and resolve operational issues with manufacturing partners and internal teams.
Responsibilities
- Monitor production-management frameworks, test environments, equipment, servers, program versions, and configurations.
- Develop and maintain programs for equipment and board control, test execution, data collection, validation, and reporting.
- Automate recurring production tasks with Python and Bash.
- Validate and deploy new or updated production programs and manage version, configuration, and recovery histories.
- Collect and analyze yield, defect-rate, test-success, and log data.
- Investigate whether failures arise from products, equipment, environment settings, or program errors.
- Improve production procedures, programs, and reporting workflows and provide technical support to manufacturing partners.