Senior Inference Engineer

📋 Description

• Build and deploy production-grade LLM inference systems across GPU machines.
• Design and operate model-serving infra using vLLM, SGLang, TensorRT-LLM.
• Optimize workloads for latency, throughput, and cost.
• Develop robust infra with Python or Golang for production use.

🎯 Requirements

• Extensive experience building/operating production infra.
• Production deployment of LLMs (vLLM, SGLang, TensorRT-LLM, etc.).
• Expertise in quantization, batching, caching, routing techniques.
• Strong Python or Golang production code skills.
• Understanding of production inference architectures.
• Problem-solving and independent investigation skills.

🎁 Benefits

• Competitive compensation including equity.
• Health, dental, vision, life insurance; dependents coverage where available.
• Benefits adapted to country of employment.
• Remote-friendly, flexible schedule and global team.
• Ownership of architecture and roadmap for inference platform.
• Collaboration with senior leadership and product teams.