Software Engineer — AI Model Bring-Up

Job Title

Software Engineer — AI Model Bring-Up

Role Summary

Join the AI Models / System Bring-Up team to port, validate, and optimize AI models on Tenstorrent accelerator platforms. The role bridges models, runtime software, and hardware to make research and production models run stably and efficiently on Tenstorrent systems.

Experience Level

Mid-level (Level - Mid-Career). Candidates at various levels will be considered; final level and offer will be determined during the interview process.

Responsibilities

Primary responsibilities focus on bringing models to Tenstorrent hardware and ensuring they run correctly and performantly.

• Port and optimize AI models (LLMs, CNNs, recommendation, vision) to Tenstorrent hardware.
• Integrate models into Tenstorrent toolchains and runtime environments.
• Design and run experiments to evaluate accuracy, performance, and stability.
• Debug cross-stack issues spanning model, runtime, compiler, and hardware layers.
• Collaborate closely with hardware, compiler, runtime, and customer/field teams during bring-up and deployment.
• Contribute to automation, regression testing, and performance tuning for model bring-up workflows.

Requirements

Required skills and capabilities; listed as must-have and nice-to-have.

Must-have

• Hands-on experience running deep learning models in a major framework (PyTorch, TensorFlow, or JAX).
• Strong programming skills in Python or C++ and familiarity with neural network architectures, training, and inference basics.
• Experience developing in Linux and debugging issues across software, runtime, and hardware layers.
• Business-level Japanese and sufficient English to work in a global team setting.
• Ability to work on-site in Tokyo under a hybrid schedule.
• Must be eligible to access U.S. export-controlled technology; employment may be contingent on citizenship, permanent residency, or prior license approval.

Nice-to-have

• Experience with LLM/foundation model inference (KV-cache optimization, quantization).
• Background in compiler or runtime engineering for ML workloads.
• Exposure to post-silicon validation, board bring-up, firmware, or accelerator platforms.
• Experience working directly with customers or field teams on AI workload deployment and debugging.
• Strong spoken English for technical discussions with global teams.

Education Requirements

Bachelor's degree in Computer Science, Engineering, Applied Mathematics or a related technical field, or equivalent practical experience.

About the Company

Company: Tenstorrent

Headquarters: Austin, Texas, United States

Tenstorrent is a technology company focused on designing innovative computing solutions. They are known for their expertise in the development of advanced hardware, including ASICs and SoCs, aimed at enhancing performance and efficiency in various applications.