Research Engineer, Post-Training Inference

📋 Description

• Design and build systems for customizing open-source models
• Integrate Model Shaping and Inference platforms for seamless post-training to serving
• Add features to inference engines for large-scale post-training experiments, incl. RL
• Ensure service stability with on-call coverage and 24/7 availability

🎯 Requirements

• 2+ years building and deploying ML-based services in production
• Hands-on with modern inference engines (SGLang, vLLM, TensorRT-LLM)
• Familiar with latest LLMS fine-tuning methods
• Strong software engineering in Python or Go
• Stay updated on ML advances

🎁 Benefits

• Startup equity
• Health insurance
• Other benefits