Principal Compiler Engineer – MLIR & AI Silicon

Ericsson GmbH; Austin, Northern (TX, KY); Hybrid; USD 150,000 - 230,000; Full time

Job summary

Ericsson in Austin, Texas is seeking a Principal Staff Compiler Engineer to lead the technical direction of a MLIR-based compiler and inference stack for custom AI silicon used in baseband processing. You will design, code, review, and profile critical subsystems while mentoring a growing team.

This hands-on leadership role requires you to ship software and collaborate with hardware architects, runtime developers, and AI researchers to shape both the compiler and the team's approach.

Qualifications

• Production compiler design experience with hands-on ownership of subsystems.
• Strong C++ and compiler infrastructure expertise.
• Hands-on MLIR/LLVM experience at scale.
• Ability to lead complex technical programs across teams.
• Experience mentoring senior engineers.

Responsibilities

• Own the technical direction of the compiler stack across model import, lowering, scheduling, memory planning, and code generation.
• Design and implement the hardest compiler subsystems, the ones that determine performance and correctness goals.
• Define MLIR dialect hierarchy, lowering strategy, and pass pipelines in collaboration with the team.
• Lead hardware-software co-design discussions, partnering with hardware architects to influence ISA, memory hierarchy, and synchronization.
• Mentor Staff and Senior compiler engineers, and shape technical growth of the team.

Skills

Production compiler

C++

MLIR/LLVM

Leadership

Mentoring

Hardware collaboration

Tools

MLIR

LLVM

Job description

Ericsson in Austin, Texas is seeking a Principal Staff Compiler Engineer to lead the technical direction of a MLIR-based compiler and inference stack for custom AI silicon used in baseband processing. You will design, code, review, and profile critical subsystems while mentoring a growing team.

This hands-on leadership role requires you to ship software and collaborate with hardware architects, runtime developers, and AI researchers to shape both the compiler and the team's approach.