Senior Inference Engineer

📋 Description

• Build and deploy production-grade LLM inference systems across GPU machines.
• Design and operate model-serving infra with vLLM, SGLang, TensorRT-LLM.
• Optimize latency, throughput, reliability, and cost.
• Apply quantization, batching, caching, and routing for performance.
• Develop infra in Python or Golang with scalable, maintainable code.
• Own initial inference platform with CTO and evolve it as the org scales.

🎯 Requirements

• Extensive experience building and operating production software or infra systems.
• Experience deploying LLMs in production (vLLM, SGLang, TensorRT-LLM or similar).
• Expertise optimizing workloads via quantization, batching, routing, etc.
• Strong Python or Golang production-grade coding skills.
• Understanding of production inference architectures from request to response.
• Excellent problem-solving and independent diagnostic ability.

🎁 Benefits

• Competitive package including equity.
• Health, dental, vision, life insurance; dependents coverage where available.
• Country-specific benefits.
• Flexible, outcome-driven schedule and remote-first environment.
• Global distributed team and significant ownership over architecture.
• Direct collaboration with senior leadership and Product teams.