Artificial Intelligence Software Library Technical Lead

Enchargeai in Santa Clara, CA or Princeton, NJ

Role/Responsibilities:

EnCharge AI is looking for an exception technical leader who can help us build out high-performance optimized libraries for our Edge AI Artificial Intelligence chips. You must have an excellent track record of building out libraries for various platforms (CPU and / or accelerator architectures) and enabling high-performance kernels in these architectures. This position is also a strong growth opportunity, with the possibility of transitioning into further leadership roles in the coming years.

  • Defining the overall strategy and execution plan for core-level libraries for optimized AI Inference deployment on EnCharge Hardware.
  • Work closely with the compiler team to define and execute on the primary set of optimized AI library templates (hand-written in EnCharge assembly) that’d be used for code-generation in AI Inference applications.
  • Work closely with the AI Hardware, Compiler, Performance & FPGA teams to determine the performance of these AI libraries and compiled binaries and to propose microarchitecture, ISA, library & compiler changes to further improve runtime performance.
  • Interface / work closely with teams building chip-simulators, performance models, assemblers, and disassemblers for the EnCharge architecture.
  • Hire, build and lead large, cross-functional, and geographically dispersed teams.
  • Mentor / lead junior engineers across the company.

Qualifications/Required Skills:

  • Masters/Ph.D. in EE/CS with >5 years of industry experience in chip-design, architecture & systems.
  • Proficiency with C++, Python and Systems programming.
  • Deep knowledge of architectures (and instruction-sets), microarchitectures, system design and performance optimizations.
  • >5 years of experience building software libraries for various architectures.
  • >3 years of experience with managing software teams.
  • Solid understanding of AI Applications, kernels, and performance bottlenecks.
  • Experience with building performance models and simulators for new architectures.
  • Knowledge of industry-standard (and advanced) tools and methodologies.
  • Excellent verbal and written communication skills.

Preferred/Beneficial Skills:

  • Knowledge of the end-to-end runtime stack for AI applications.
  • Experience with CI/CD.
  • Knowledge of AI Compiler stacks.

Apply