🛠 Tech Stack

💼 About This Role

You'll analyze latest ML workloads like multi-modal LLMs and generative inference for next-gen hardware. Your work will directly shape HW/SW co-design for datacenter accelerators at a generative AI startup. You'll collaborate across architecture, product, and compiler teams.

🎯 What You'll Do

• Analyze multi-modal LLMs and video/audio-generation workloads
• Develop analytical performance models for current and future hardware
• Propose new HW/SW features to accelerate ML algorithms
• Collaborate with product, hardware, compiler, and inference teams

📋 Requirements

• BSEE with 10+ years or MSEE with 8+ years industry experience
• Solid grasp of computer architecture, HW/SW co-design, performance modeling, ML fundamentals
• Programming fluency in C/C++ or Python
• Experience with analytical performance models and architecture simulators

✨ Nice to Have

• Research background with publications in ISCA, MICRO, ASPLOS, etc.
• Experience with emerging hardware technologies like DIMC, 3D-DRAM

🎁 Benefits & Perks

• 🏖️ Unlimited PTO
• 🏥 Health insurance
• 📈 Equity
• 🍕 Free lunch
• 🏢 Hybrid work