Junior System Modeling

<h3><strong>About Unconventional AI</strong></h3> <p>We are rethinking the foundations of the computer to optimize energy efficiency for AI. Founded by pioneers in the field - including Naveen Rao (Nervana, MosaicML) and Michael Carbin (MIT, MosaicML) - we are building a new computational substrate that interfaces directly with the physics of silicon to achieve biology-scale efficiency. We recently raised $475M in seed funding to turn this vision into reality.</p> <p>As a <strong>Junior Member of Technical Staff, System Modeling</strong>, you will work closely with senior engineers to contribute to the development of our multi-disciplinary simulation frameworks. You will assist the hands-on R&D team in building simulation environments that enable rapid iteration and testing across all layers of our unconventional physics-based computing systems for machine learning workloads. Your work will focus on integrating physics-based models, developing GPU-accelerated simulations, and supporting the cross-layer system integration necessary for "Extreme co-design".</p> <h3><strong>Key Responsibilities</strong></h3> <ul> <li><strong>Contribute to the implementation and optimization of GPU-accelerated simulators</strong> for ML on analog/unconventional hardware, focusing on specific modules and features within PyTorch.</li> <li><strong>Assist in integrating physics-based device and system models </strong>into the PyTorch simulation environment to help expose early algorithm–hardware tradeoffs and enable cross-layer optimization.</li> <li><strong>Support the maintenance and extension of the unified end-to-end simulation environment,</strong> helping to link theory, algorithms, and device models, and ensuring alignment between high-level and near-physical simulators.</li> <li><strong>Help implement and adhere to robust experiment tracking protocols</strong> to ensure simulation results, configurations, and non-idealities are reproducible and auditable.</li> <li><strong>Collaborate with Algorithms and Hardware teams</strong> to gather requirements and ensure the modeling environment meets their needs for high-level algorithm development and lower-level hardware verification.</li> </ul> <h3> </h3> <h3><strong>What We’re Looking For</strong></h3> <ul> <li><strong>Strong Systems Foundation:</strong> A BS, MS, or PhD in Computer Science, Electrical Engineering, or a related technical field. You should have a deep understanding of computer architecture and operating systems.</li> <li><strong>Coding Proficiency:</strong> Strong skills in <strong>C++</strong> and <strong>Python</strong>. You should be comfortable writing performance-critical code.</li> <li><strong>AI/ML Exposure:</strong> Basic familiarity with the internals of deep learning frameworks (e.g., how a PyTorch graph is executed) and common model architectures.</li> <li><strong>Mathematical Intuition:</strong> A solid grasp of linear algebra and calculus, which are essential for understanding both neural dynamics and hardware optimizations.</li> <li><strong>First Principles Mindset:</strong> You enjoy digging into "why" things work (or don't) and aren't afraid to challenge conventional software "best practices" to find a more efficient path.</li> </ul> <h3><strong>Bonus Points</strong></h3> <ul> <li>Experience with compilers (LLVM, MLIR) or domain-specific languages like <strong>Triton</strong>.</li> <li>Exposure to GPU programming (CUDA) or other hardware accelerators.</li> <li>Prior research or internship experience in high-performance computing (HPC) or neuromorphic systems.</li> <li>Contributions to open-source AI or systems software projects.</li> </ul> <h3><strong>Why Join Us?</strong></h3> <ul> <li><strong>Mentorship:</strong> Learn directly from the architects who built the modern AI stack at companies like Intel, Databricks, and NVIDIA.</li> <li><strong>Impact:</strong> You won't be a small cog in a giant machine. You will be helping build the machine itself.</li> <li><strong>Unconventional Problems:</strong> Work on challenges that don't have a StackOverflow answer—you’ll be defining the future of AI compute.</li> <li><strong>Competitive Package:</strong> Significant equity and competitive salary at a well-funded, high-growth startup.</li> </ul>