🛠 Tech Stack

💼 About This Role

You'll build functional and cycle-accurate simulators for our Optical Tensor Processing Unit architecture. Your models will guide hardware-software co-design and drive key technical decisions. This role sits at the crossroads of hardware, software, and ML workload analysis.

🎯 What You'll Do

• Design and maintain functional simulators of the OTPU subsystem
• Build cycle-accurate performance models for throughput and latency analysis
• Run massive parameter sweeps to guide architecture and software roadmaps
• Develop Python/C++ tooling for trace parsing and visualization

📋 Requirements

• 5+ years building performance/power models for CPUs, GPUs, or ASICs
• Strong coding ability in C++ and Python
• Experience with discrete-event or cycle-accurate simulators (e.g., gem5, SystemC)
• Solid grasp of computer architecture fundamentals (memory systems, interconnects, queuing theory)

✨ Nice to Have

• Familiarity with machine learning workloads and frameworks (PyTorch, TensorFlow, JAX)
• Comfort reading RTL or schematics
• Personal/open-source projects in simulators, ML kernels, or performance analysis

🎁 Benefits & Perks

• 💰 Competitive Salary ($211k+ CAD)
• 🏢 Equity & Ownership (meaningful stock options)
• 🏠 Living-Local Bonus ($42k CAD for residence within 20 min of office)
• 🏥 Premium Healthcare (medical and dental)
• ✈️ 25 days annual leave plus Ontario bank holidays