Offer summary

Qualifications:

At least 4 years of software engineering experience., Minimum 2 years of experience developing backends for large-scale, open-source compilers like LLVM., Experience with neural network architectures or ML accelerators., Knowledge of MLIR backend development is a plus..

Key responsibilities:

Develop an MLIR-based AI compiler for next-generation hardware.

Work with platform teams to define IRs tailored to hardware architecture.

Collaborate with runtime teams to enhance the runtime stack and AI frameworks.

Partner with toolchain teams to create comprehensive development workflows.

Job description

Description

NextSilicon is reimagining high-performance computing. Our accelerated compute solutions leverage intelligent adaptive algorithms to vastly accelerate supercomputers, driving them forward into a new generation. Our new software-defined hardware architecture enables HPC & AI to fulfill their promise of breakthroughs in all fields of advanced research.

At NextSilicon, everything we do is guided by three core values:

Professionalism: We get exceptional results through professionalism and unwavering dedication to quality and performance.
Unity: Collaboration is key to success; we foster a work environment where every employee feels valued and heard.
Impact: We're passionate about developing technologies that make a meaningful impact on industries, communities, and individuals worldwide.

The AI Compiler team is central to developing the means by which cutting-edge AI models and workflows achieve world-record results on our unique hardware architecture.

We are seeking a talented AI compiler expert to form the new team in Belgrade. In this high-visibility, hands-on role, you and your team will be building the AI compiler for NextSilicon’s next generation platforms.

Requirements

4+ years of experience in software engineering.
2+ years of experience developing a backend for a large-scale, open-source-based compiler (e.g. LLVM)
At least one of the following:
Demonstrable open-source contribution to relevant projects.
Experience developing state-of-the-art neural network architectures.
Specialization experience in ML accelerators, high performance computing, GPU and/or CPU architectures.
Backend experience with MLIR: an advantage.

Responsibilities

Develop a state-of-the-art MLIR-based AI compiler stack targeting our next generation hardware and delivering superior acceleration to AI applications.
Interface with platform teams to define IRs leveraging unique our hardware architecture.
Collaborate with runtime teams to shape the future of our runtime stack, from driver level up to integration into popular AI frameworks.
Collaborate with toolchain teams to deliver a holistic toolchain for our customers, supporting static and dynamic development workflows.

Required profile