Debugger Generation Agent Engineer - Member of Technical Staff
About the role
The role builds the agent that generates a debugger like that for a new chip, and its core is continuous checkpointing with restore-to-checkpoint: snapshot the run as it proceeds, then jump back to the instant before the hang, or before the numbers began to degrade, and inspect exactly what was and was not in memory, without rewriting code to reproduce the moment.
Responsibilities
- Build continuous checkpointing and restore functionality.
- Implement breakpoints and state inspection features.
- Develop parallel debugging capabilities.
- Design differential debugging techniques.
- Ensure compatibility across various hardware platforms.
- Refine the Corsair debugger for continuous checkpointing and real breakpoints.
- Expose the debugger's interface to agents for hypothesis testing.
Requirements
Genuine debugging depth, a real model of program state on hardware, experience with time-travel or record-replay systems, fluency in Python and a systems language, and familiarity with checkpoint-and-restore systems are essential.
Qualifications
- Experience with AI accelerators or mobile SoCs like Snapdragon and its Hexagon DSP.
- Background in hunting numerical bugs in ML.
- Firmware, bare-metal, on-chip debug, or JTAG experience.
Skills
- Python programming.
- Systems languages: Rust, C, or C++.
- Experience with time-travel or record-replay debugger technologies.
- Firmware, bare-metal, on-chip debug, or JTAG experience.
- Knowledge of checkpoint-and-restore systems.
Benefits
Competitive compensation package, benefits, and opportunities for growth within a rapidly expanding AI infrastructure research company.
Pay
$200,000.00 - $300,000.00
Schedule
Full-time