Senior AI GPU Infrastructure Engineer

Clockwork Systems, Inc.; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Catered lunch

Competitive compensation

Great benefits package

Job summary

Clockwork Systems is building infrastructure for fault-tolerant, high-performance distributed GPU training. You will work at the intersection of GPU systems, high-speed networking, and distributed coordination—designing and implementing systems at scale.

The role requires deep systems-building experience, strong C/C++ skills, and the ability to reason about distributed behavior. You will lead end-to-end design through production and contribute to a friendly, inclusive team with competitive

Qualifications

• Requires systems-building experience.
• Experience with distributed storage, databases, or coordination systems.
• Familiarity with runtimes, profilers, or performance tooling.
• Experience with high-performance network stacks and I/O systems.

Responsibilities

• Design and implement low-level systems software for GPU clusters.
• Modify and extend frameworks like PyTorch, NCCL, CUDA runtime.
• Build components to improve reliability and efficiency of large-scale GPU training.
• Debug complex distributed/concurrent systems with subtle failures.
• Own systems end-to-end from design to production.

Skills

C/C++ (systems)

Concurrency

Distributed systems

Performance profiling

GPU programming (CUDA)

Tools

PyTorch internals

NCCL

CUDA runtime

Job description

Clockwork Systems is building infrastructure for fault-tolerant, high-performance distributed GPU training. You will work at the intersection of GPU systems, high-speed networking, and distributed coordination—designing and implementing systems at scale.

The role requires deep systems-building experience, strong C/C++ skills, and the ability to reason about distributed behavior. You will lead end-to-end design through production and contribute to a friendly, inclusive team with competitive