AI Inference Compiler Technical Director

Flex Logix is developing industry-leading AI inference engines and we are the #1 provider of eFPGA solutions.  Our InferX X1 is the industry’s fastest and most-efficient AI edge inference accelerator that will bring AI to the masses in high-volume applications, surpassing competitor’s performance at lower size, price and power. We recently completed a $55M funding round.

Our Inference Compiler is part of our software stack, supporting the chip. Production shipment and compiler availability commences beginning-2022. Our architecture is covered by dozens of patents and is highly differentiated giving us a sustainable competitive advantage. Read more about nnMAX Reconfigurable Tensor Processor and InferX on our Inference page at www.flex-logix.com

Flex Logix is a rapidly expanding, high growth company and is seeking a very strong Technical Director with experience in ML inference acceleration to take our Compiler to the next level.

The right candidate needs to be able to lead expansion of our Compiler to support breadth of NN Models. The Compiler is written in modern C++ language, therefore the ideal candidate needs to be fluent in the modern C++ programming paradigms, OO design and building useful domain-specific software abstractions.

Responsibilities

• Lead a part of our growing Inference Compiler team, reporting to the VP of Inference SW Development
• Work with marketing on customer’s ML model requirements and definitions
• Lead the expansion of functionality of our Compiler to support new ML models
• Work on architecture and design of the feature support in Compiler software as it relates to support of specific Operators and Graph topologies
• Conduct design and code reviews, promote communication and good design practices across the team
• Partition the coding work into components and assign them to developers for implementation
• Create schedules and plans around tasks and track implementation progress
• Lead code development, participate in implementation personally

Requirements

• 8+ years of relevant industry experience in system-level software development in C++ language
• Experience in developing software for ML model inference acceleration
• Good understanding of hardware architecture and, ideally, Verilog programming, as it pertains to inference acceleration
• Excellent understanding of software/hardware development engineering practices, workflow, schedule dependencies