HPC Systems Lead & Architect — Silicon to Server Bring-up

Bitdeer; Singapore; Sur place; SGD 180 000 - 240 000; Plein temps

Avantages offerts par ce poste

Welfare benefits

Training and mentoring

Open workspaces

Autonomy and growth opportunities

Résumé du poste

Bitdeer in Singapore is seeking a leader to productize high-performance computing chips across silicon, boards, firmware, drivers and servers—from bring-up to production and customer delivery. You will own technical readiness, system performance and stability.

Responsibilities include translating inference workloads into hardware requirements, leading cross-layer debugging, validation and delivery, and coordinating with ODM/JDM teams to balance schedule, cost and performance.

Qualifications

• Degree in electrical or computer engineering or equivalent expertise.
• Led at least one server or accelerator platform through full cycle.
• Deep expertise in board hardware, firmware or low-level software.
• Strong cross-layer diagnostic ability covering PCIe, memory, power/reset, Linux drivers and BIOS/BMC interactions.
• Excellent English communication and on-site availability in Singapore.

Responsabilités

• Translate inference workloads into board, host, interconnect, power, cooling and serviceability requirements.
• Lead silicon bring-up, cross-layer diagnosis, and verification of fixes.
• Define workloads and tests for sustained operation, recovery and production.
• Coordinate engineering teams and ODM/JDM design/validation deliverables while managing trade-offs.

Connaissances

Server platform bring-up

Cross-layer debugging

Hardware-software co-design

Linux drivers

PCIe, power, cooling

Diagnosis and root-cause analysis

Technical leadership

ODM/JDM coordination

Formation

Electrical/Computer Engineering degree

Outils

BIOS/BMC

Linux

Description du poste

Bitdeer in Singapore is seeking a leader to productize high-performance computing chips across silicon, boards, firmware, drivers and servers—from bring-up to production and customer delivery. You will own technical readiness, system performance and stability.

Responsibilities include translating inference workloads into hardware requirements, leading cross-layer debugging, validation and delivery, and coordinating with ODM/JDM teams to balance schedule, cost and performance.