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 inference workloads for latency, throughput, reliability, cost
• Apply quantization, batching, caching, routing to boost perf
• Develop infra in Python or Golang with scalable engineering focus
• Partner with CTO to shape initial inference platform and roadmap

🎯 Requirements

• Significant experience building/operating production software or infra
• Production deployment of large language models (vLLM, SGLang, TensorRT-LLM, or equivalent)
• Optimization techniques: quantization, batching, caching, routing
• Strong Python or Golang production code skills
• Understand end-to-end inference architecture from request to response
• Excellent problem-solving and independent investigation skills

🎁 Benefits

• Competitive package with equity
• Health/dental/vision/life insurances
• Benefits tailored to country of employment
• Remote-friendly with flexible schedule
• Global distributed team with ownership and impact
• Work on GPU/AI infra at scale and open-source tech