Senior Inference Engineer (Remote from Poland)

📋 Description

• Build and deploy production-grade LLM inference systems across GPU machines.
• Design and operate model-serving infrastructure (vLLM, SGLang, TensorRT-LLM).
• Optimize inference workloads for latency, throughput, reliability, and cost.
• Apply quantization, batching, caching, and routing techniques to improve performance.
• Develop production infrastructure using Python or Golang with maintainable code.
• Own the inference platform evolution with CTO collaboration.

🎯 Requirements

• Significant experience building/operating production software or infra systems.
• Experience deploying/serving LLMs in production (vLLM, SGLang, TensorRT-LLM or similar).
• Experience optimizing inference workloads via quantization, batching, caching, routing.
• Strong Python or Golang production coding experience.
• Understanding of production inference architectures from user request to served response.
• Excellent problem-solving and independent debugging skills.

🎁 Benefits

• Competitive compensation including equity.
• Health, dental, vision, life insurance, with dependents where available.
• Country-specific benefits where applicable.
• Flexible, outcomes-focused schedule.
• Remote-first environment with distributed team.
• Ownership of architecture and long-term roadmap of the inference platform.