Senior Compiler Engineer, AI IP

Location: Hybrid, based in Belgrade, Serbia

Company

Tenstorrent develops high-performance AI platforms, RISC-V CPUs, semiconductor technology, and AI acceleration IP for customer SoCs.

What you will do

• Bring machine learning models into Tenstorrent AI IP workflows and customer products.
• Work across model, compiler, runtime, software, hardware, and IP layers.
• Investigate model compatibility and validate that integrations produce correct results.
• Help customers resolve technical questions, integration challenges, and customer-specific requirements.
• Collaborate with software, compiler, hardware, and IP engineers to improve model compatibility and customer outcomes.

Requirements

• Strong C++ skills and experience developing, debugging, or maintaining production-quality software.
• Hands-on experience with ONNX or similar model formats and workflows, including model conversion, graph inspection or transformation, operator support, or runtime integration.
• Experience bringing models into a software runtime or hardware platform and validating integration correctness.
• Working knowledge of machine learning fundamentals and common model architectures, especially computer vision models and large language models.
• Ability to investigate model compatibility and translate ambiguous customer requirements into workable solutions.
• Eligibility to access U.S. export-controlled technology may be required; employment can depend on citizenship, permanent residency, or prior license approval.

Nice to have

• Experience with compilers, MLIR, graph optimization, runtimes, or code generation.
• Customer-facing engineering or technical support experience.

Culture & Benefits

• Collaborative environment focused on curiosity and solving difficult technical problems.
• Exposure to real-world AI workloads and customer product integrations.
• Competitive compensation package and benefits.
• Equal opportunity employment.