🛠 Tech Stack

💼 About This Role

You'll join the Model Performance team to implement cutting-edge techniques for ML model inference. You will optimize large language models and deep dive into codebases like TensorRT and PyTorch to debug performance issues.

🎯 What You'll Do

• Implement quantization, speculative decoding, and other inference techniques.
• Debug ML performance issues in TensorRT, PyTorch, and CUDA codebases.
• Apply optimization techniques across a range of ML models.
• Own projects from idea to production.

📋 Requirements

• Bachelor's or higher in Computer Science, Engineering, or related field.
• Experience with Python or C++.
• Familiarity with LLM optimization techniques like quantization.
• Strong familiarity with PyTorch, TensorRT, or TensorRT-LLM.

✨ Nice to Have

• Proficiency in enhancing performance of LLM software systems.
• Experience with CUDA or similar technologies.
• Experience with Docker and Kubernetes.

🎁 Benefits & Perks

• 📅 Flexible PTO including company-wide Winter Break.
• 🏥 100% coverage of medical, dental, and vision insurance for employee and dependents.
• 👶 Paid parental leave and fertility stipend through Carrot.
• 💰 Competitive compensation including meaningful equity.