Senior ML Engineer

Job Summary

To drive inference optimization at Kimchi, the full-time Senior ML Engineer will enhance throughput, reduce latency, and optimize KV cache utilization while working remotely in a high-autonomy role focused on building efficient ML systems.

Key responsibilities

• Push throughput through continuous batching, kernel-level tuning, and optimizing GPU performance
• Cut latency by profiling and addressing bottlenecks in compute, memory bandwidth, and scheduling
• Quantize models without quality regression and improve KV cache utilization for enhanced throughput

Required qualifications

• 5+ years of experience building real ML systems with a focus on inference or training infrastructure
• Strong proficiency in Python for production services
• Hands-on experience with vLLM, SGLang, or TensorRT-LLM, and understanding of inference engine performance
• Fluency with quantization tradeoffs and practical experience in distributed systems
• A bias toward measurement and self-direction in a broad mandate role