Unconventionalinc
AI Silicon, Silicon Validation Engineer
Mountain View, CA. Posted 4 months ago
The role
You will drive post-silicon bring-up, validation, and characterization of core components for a novel computing platform. This role involves working at the intersection of AI, physics, and computer architecture.
What you will do
- Lead the initial power-on and bring-up of new silicon prototypes and hardware platforms in the lab.
- Evaluate and benchmark the functionality, performance, and power consumption of complex mixed-signal circuits.
- Utilize lab test equipment to identify, triage, and solve anomalies across silicon, board, and software.
- Design and maintain Python-based automation frameworks.
- Collaborate with System Modeling and Analog and Digital Design teams to define validation requirements and drive root-cause analysis.
Required qualifications
- B.S. or M.S. in Electrical Engineering, Computer Engineering, or a related field.
- 5+ years of industry experience in post-silicon bringup-up, hardware validation, or silicon characterization.
- Familiarity with operating lab test equipment (oscilloscopes, logic analyzers, power analyzers, etc).
- Demonstrated proficiency in characterizing and debugging mixed-signal circuits.
- Experience with Python programming and lab automation.
- Excellent written and verbal communication skills.
Nice to have
- Experience evaluating the performance tradeoffs of current neural network architectures.
- Experience with correlating mixed-signal measurements on silicon to simulation models.
- Understanding of hardware/software co-design concepts for machine learning inference or training.
- Familiarity with FPGA emulation and RTL simulation to leverage pre-silicon verification for post-silicon bring-up.
- Familiarity with AI automation.
Benefits
- Best-in-class health benefits
- 401k matching
- Truly unlimited PTO
- Complimentary meals in our Palo Alto office
About the company
Unconventional is rethinking computing from the ground up to build a new foundation for AI that is 1000x more efficient by exploiting the rich physics of semiconductors.