🛠 Tech Stack

💼 About This Role

You'll design and implement the front-end pipeline for FuriosaAI's compiler, translating models from frameworks like PyTorch into internal IR. You'll develop graph-level optimizations and evolve a tensor-level kernel language. This role is central to building high-performance AI systems.

🎯 What You'll Do

• Design and implement front-end pipeline from ML frameworks to internal IR
• Develop graph-level optimizations like operator fusion and shape inference
• Build extensible model ingestion for new architectures
• Design tensor-level kernel language as user interface to compiler IR

📋 Requirements

• Bachelor's in Computer Science or related field
• Experience with compilers or program transformation systems
• Understanding of deep learning frameworks (PyTorch, TensorFlow, ONNX)
• Proficiency in Python and a systems language like Rust or C++

✨ Nice to Have

• Master's or PhD in compilers or programming languages
• Experience with DSLs or user-facing programming models
• Knowledge of PyTorch compiler internals or Triton

🎁 Benefits & Perks

• 🏖️ Flexible work environment
• 💻 Cutting-edge AI hardware projects
• 📚 Learning budget for conferences and courses

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter phone screen· 30 min
2. 2Technical interview· 60 min
3. 3Hiring manager interview· 45 min
4. 4Offer· 1 week

[email protected]