Senior Machine Learning Systems Engineer

대규모 모델 서빙 시스템을 end-to-end로 설계 및 최적화, distributed infrastructure 구축(load balancing, auto-scaling, batch scheduling, global KV cache), production workload에서 inference latency/throughput 최적화, billions of requests를 안정적으로 처리하는 high-concurrency serving system 개발, inference engine benchmarking/fine-tuning/acceleration, CI/CD 인프라 구축을 통한 model deployment 및 inference engine update 자동화, senior ML engineers와 협업하여 open-source LLM fine-tuning 및 배포.

필수: 5+ years of software engineering experience, 2+ years of system performance optimization experience, Deep low-level systems programming (C/C++ or Rust), Experience with large-scale, high-concurrent production serving, Experience with GPU inference engines (vLLM, SGLang, Triton, TensorRT-LLM, etc.), Strong background in system optimizations such as batching, caching, load balancing, parallelism. 우대: Low-level inference optimizations(GPU kernels), Algorithmic inference optimizations(quantization, speculative decoding, distillation), testing/benchmarking/reliability 경험, inference용 CI/CD 설계 및 구현 경험.