Senior Inference Engineer

📋 Description

• Build and deploy production-grade LLM inference systems across GPUs
• Design and operate model-serving infra with vLLM, SGLang, TensorRT-LLM
• Optimize workloads for latency, throughput, and costs
• Apply quantization, batching, caching, and routing techniques
• Develop robust infra using Python or Golang with scalable code
• Own initial inference platform with CTO collaboration

🎯 Requirements

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

🎁 Benefits

• Competitive compensation including equity
• Health benefits and dependents coverage where available
• Country-specific benefits; remote-friendly schedule
• Remote-first, globally distributed team
• Ownership over architecture and roadmap
• Direct collaboration with senior leadership and Product teams