Principal Engineer, AI Compiler

Overview

Tenstorrent is leading the industry on cutting-edge AI technology, revolutionizing performance expectations, ease of use, and cost efficiency. We are growing our team and looking for contributors of all seniorities. Join the team revolutionizing AI computing at Tenstorrent.

In this role you will lead development on TT-Forge, our MLIR-based compiler, and manage a team focused on scaling graph transformations, lowering passes, and kernel-level optimizations. You’ll help shape the future of AI computing through compiler technology that is fast, flexible, and built for real-world models. This role is hybrid based in Austin, TX.

We welcome candidates at various experience levels. During the interview process, candidates will be assessed for the appropriate level, and offers will align with that level, which may differ from the one in this posting.

• Leadership to drive compiler development across multiple layers of the stack, including custom dialects, transformation passes, and runtime integration.
• Alignment with hardware, software, and ML teams to ensure the compiler supports realistic performance and deployment needs.
• Technical ownership of roadmap priorities, planning, and mentorship for a high-performing engineering team.
• Insight to identify bottlenecks, debug performance issues, and improve developer workflows across the stack.

• Extensive experience building compilers or similar systems, with strong fluency in C++ and Python.
• Strong knowledge of MLIR, LLVM, or related infrastructure, with hands-on work in dialect design or optimization passes.
• You have a strong understanding of modern AI frameworks like PyTorch, Tensor Flow, or JAX, including how models are transformed and executed.
• A background in working across teams to ship reliable, scalable tools in fast-paced engineering environments.

• How to build compiler infrastructure that supports both training and inference at scale across custom chip architectures.
• New approaches for human-in-the-loop optimization using TT-Explorer and other internal tooling.
• Best practices for evolving MLIR dialects like TTIR, TTNN, and TTKernel to support next-generation AI workloads.
• How Tenstorrent delivers open, performant, and developer-friendly AI infrastructure that scales with industry demands.

Note:

Compensation information is provided as part of the original posting. The following line indicates compensation range and is retained here for completeness: “Compensation for all engineers at Tenstorrent ranges from $100k - $500k including base and variable compensation targets. Experience, skills, education, background and location all impact the actual offer made.”

Tenstorrent offers a highly competitive compensation package and benefits, and we are an equal opportunity employer.

This offer of employment is contingent upon the applicant being eligible to access U.S. export-controlled technology. Due to U.S. export laws, including EAR, the Company must ensure compliance when transferring technology to nationals of certain countries. The offer may be contingent upon citizenship/permanent residency status or license approval by the U.S. Commerce Department or applicable agency. If employment is not possible due to export laws, any offer may be rescinded.