Senior MTIA DevTools Engineer

Meta; Bellevue (WA); On-site; USD 184,000 - 257,000; Full time

Benefits offered by this job

Bonus

Equity

Benefits

Job summary

Meta seeks a Software Engineer to advance MTIA SW Tooling, building developer tools for debugging, profiling, and monitoring AI workloads on MTIA hardware. You will work across the stack—from compiler to hardware—designing tools that improve developer productivity and fleet observability.

You will own the technical roadmap for tooling areas, collaborate with cross-functional teams, and drive AI-native approaches and diagnostics to reduce time-to-root-cause.

Qualifications

• Experience building debugging, profiling, or diagnostic tools for complex systems.
• Proficiency in C++ and Python with low-level systems programming.
• Experience across compiler, runtime, OS/driver, and hardware layers.
• Track record delivering tooling projects from inception through production.

Responsibilities

• Own the technical vision and roadmap for MTIA developer tooling.
• Design and develop debugging tools including graph-mode debugging.
• Contribute to MTIA tooling infrastructure for profiling and memory analysis.
• Collaborate with MTIA compiler, runtime, kernel, and hardware teams.
• Drive AI-native tooling approaches using automation and diagnostics.
• Partner with product teams to understand developer pain points and prioritize tooling investments.
• Advise on tooling best practices and communicate architectural decisions.

Skills

C++

Python

Debugging tools

Performance engineering

Cross-stack debugging

Linux kernel

Tooling infrastructure

Education

Bachelor's degree in Computer Science or related field

Tools

gdb

perf

nsight-compute

cuda-gdb

ELF/DWARF

eBPF

Valgrind

LLVM sanitizers

Job description

Meta seeks a Software Engineer to advance MTIA SW Tooling, building developer tools for debugging, profiling, and monitoring AI workloads on MTIA hardware. You will work across the stack—from compiler to hardware—designing tools that improve developer productivity and fleet observability.

You will own the technical roadmap for tooling areas, collaborate with cross-functional teams, and drive AI-native approaches and diagnostics to reduce time-to-root-cause.