About the Role
Validate and optimize AI models on Tenstorrent platforms, port models to toolchains, evaluate model performance, and debug issues across software, runtime, and hardware.
Requirements
Bring up, validate, and optimize various AI models (LLMs, CNNs, recommendation, vision) on Tenstorrent hardware and simulators, port models to toolchains, run experiments, and debug cross-stack issues. Requires experience with deep learning frameworks (PyTorch, TensorFlow, JAX), strong Python/C++ skills, and comfort with Linux.
Full Job Description
<div class="content-intro"><p>Tenstorrent is leading the industry on cutting-edge AI technology, revolutionizing performance expectations, ease of use, and cost efficiency. With AI redefining the computing paradigm, solutions must evolve to unify innovations in software models, compilers, platforms, networking, and semiconductors. Our diverse team of technologists have developed a high performance RISC-V CPU from scratch, and share a passion for AI and a deep desire to build the best AI platform possible. We value collaboration, curiosity, and a commitment to solving hard problems. We are growing our team and looking for contributors of all seniorities.</p></div><h2 data-pm-slice="1 3 []">About Tenstorrent</h2>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Tenstorrent is leading the industry on cutting-edge AI technology, revolutionizing performance expectations, ease of use, and cost efficiency. With AI redefining the computing paradigm, solutions must evolve to unify innovations in software models, compilers, platforms, networking, and semiconductors. Our diverse team of technologists have developed a high performance RISC-V CPU from scratch, and share a passion for AI and a deep desire to build the best AI platform possible. We value collaboration, curiosity, and a commitment to solving hard problems. We are growing our team and looking for contributors of all seniorities.</p>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">This role sits at the intersection of technical expertise and customer engagement, focused on helping customers and internal teams bring up and optimize AI models on Tenstorrent platforms.</p>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">This role is hybrid, based out of Tokyo, Japan.</p>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">We welcome candidates at various experience levels for this role. 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.</p>
<h2>Tenstorrentについて</h2>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Tenstorrentは、最先端のAI技術で業界をリードし、性能、使いやすさ、コスト効率の常識を変えています。AIによってコンピューティングのあり方が再定義される中、ソフトウェアモデル、コンパイラ、プラットフォーム、ネットワーキング、半導体における技術革新を一体として進化させることが求められています。Tenstorrentの多様な技術者チームは、高性能なRISC-V CPUをゼロから開発してきました。そして、AIへの情熱と、最高のAIプラットフォームをつくりたいという強い思いを共有しています。私たちは、コラボレーション、好奇心、そして難しい課題に真摯に向き合う姿勢を大切にしています。現在、さまざまなレベルの方を歓迎しながらチームを拡大しています。</p>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">このポジションは、技術的な専門性と顧客・社内連携の両方が求められる役割であり、顧客や社内チームがTenstorrentプラットフォーム上でAIモデルを立ち上げ・最適化できるよう支援することにフォーカスしています。</p>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">本ポジションは日本・東京を拠点としたハイブリッド勤務です。</p>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">本ポジションでは、さまざまな経験レベルの候補者を歓迎しています。面接プロセスを通じて適切なレベルを判断し、オファー内容はそのレベルに応じて決定されるため、本求人票上のレベル表記と異なる場合があります.</p>
<h2>About the Role</h2>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">As a Software Engineer on the AI Models / System Bring-Up team, you will help bring up, validate, and optimize AI models on Tenstorrent platforms. You will work across models, runtime software, and hardware to turn research workloads into reliable, high-performance systems.</p>
<h2>募集ポジションについて</h2>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">AI Models / System Bring-UpチームのSoftware Engineerとして、Tenstorrentプラットフォーム上でAIモデルの立ち上げ、検証、最適化を担当していただきます。モデル、ランタイムソフトウェア、ハードウェアを横断して、研究段階のワークロードを安定した高性能システムへとつなげていくポジションです。</p>
<h2>Who You Are</h2>
<ul>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Experience with deep learning models in at least one major framework such as PyTorch, TensorFlow, or JAX.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Strong Python or C++ skills and good understanding of neural network architectures, training, and inference workflows.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Comfortable working in Linux and able to debug issues across software, runtime, and hardware.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Collaborative and curious, with a degree in Computer Science, Engineering, Applied Mathematics, or a related field, or equivalent practical experience.</p>
</li>
<li>Fluent in English; Japanese proficiency is preferred.</li>
</ul>
<h2>求める人物像</h2>
<ul>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">PyTorch、TensorFlow、JAXなど、主要な深層学習フレームワークのいずれかでのモデル実務経験をお持ちの方</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">PythonやC++に強みがあり、ニューラルネットワークの構造、学習、推論の基本理解がある方</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Linux環境での開発に慣れており、ソフトウェア・ランタイム・ハードウェアをまたぐ課題のデバッグができる方</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">協調性と好奇心があり、Computer Science、Engineering、Applied Mathematics関連の学位、または同等の実務経験をお持ちの方</p>
</li>
<li>ビジネスレベル日本語と業務遂行が可能な英語力がある方</li>
</ul>
<h2>What We Need</h2>
<ul>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Bring up and validate AI models such as LLMs, CNNs, recommendation models, and vision models on Tenstorrent hardware and simulators.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Port models into Tenstorrent toolchains and runtime environments.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Run experiments to evaluate model accuracy, performance, and stability.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Debug cross-stack issues and work closely with hardware, compiler, and runtime teams.</p>
</li>
</ul>
<h2>お任せする業務</h2>
<ul>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">LLM、CNN、推薦モデル、ビジョンモデルなどのAIモデルをTenstorrentのハードウェアおよびシミュレータ上で立ち上げ、検証すること</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">モデルをTenstorrentのツールチェーンおよびランタイム環境へ移植・統合すること</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">モデルの精度、性能、安定性を評価するための実験を設計・実施すること</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">スタック横断の課題をデバッグし、ハードウェア、コンパイラ、ランタイムの各チームと密に連携すること</p>
</li>
</ul>
<h2>What You Will Learn</h2>
<ul>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">How AI models are mapped and optimized on custom AI accelerators.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">How hardware, compiler, runtime, and model teams work together to build production-ready systems.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Best practices for model bring-up, automation, regression testing, and performance tuning.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">How to translate real-world model requirements into practical technical solutions.</p>
</li>
</ul>
<h2>このポジションで得られること</h2>
<ul>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">カスタムAIアクセラレータ上でAIモデルをどのように動かし、最適化していくか</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">ハードウェア、コンパイラ、ランタイム、モデルの各チームがどのように連携して実運用向けシステムを作るか</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">モデルbring-up、自動化、回帰テスト、性能チューニングのベストプラクティス</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">実際のモデル要件を、実用的な技術ソリューションへ落とし込む方法</p>
</li>
</ul>
<h2>Nice to Have</h2>
<ul>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Experience with LLM or foundation model inference, including KV-cache optimization and quantization.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Background in compiler or runtime engineering for ML workloads.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Exposure to post-silicon validation, board bring-up, firmware development, or accelerator platforms.</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">Experience working directly with customers or field teams on AI workload deployment and debugging.</p>
</li>
</ul>
<h2>歓迎要件</h2>
<ul>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">LLMまたは基盤モデル推論の経験(KV-cache最適化、量子化を含む)</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">MLワークロード向けのコンパイラまたはランタイム開発の経験</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">ポストシリコン検証、ボードbring-up、ファームウェア開発、アクセラレータ基盤に関する経験</p>
</li>
<li>
<p class="wnfdntf _1ibi0s3f3 _1ibi0s3ce _1ibi0s3e8">AIワークロードの導入やデバッグで、顧客やフィールドチームと直接連携した経験</p>
</li>
</ul><div class="content-conclusion"><p><em>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 those codified in the U.S. Export Administration Regulations (EAR), the Company is required to ensure compliance with these laws when transferring technology to nationals of certain countries (such as EAR Country Groups D:1, E1, and E2). These requirements apply to persons located in the U.S. and all countries outside the U.S. As the position offered will have direct and/or indirect access to information, systems, or technologies subject to these laws, the offer may be contingent upon your citizenship/permanent residency status or ability to obtain prior license approval from the U.S. Commerce Department or applicable federal agency. If employment is not possible due to U.S. export laws, any offer of employment will be rescinded.</em></p></div>