Senior ML Engineer | Kimchi (LLM Inference Optimization)

Onsite

pythonnodeawskubernetesgcpazurepytorch technology

arbeitnow

Match & cover letter

Create a profile to see your match and get a cover letter for this role.

Create profile and match

Job description

You will optimize LLM inference performance at Kimchi, focusing on throughput and latency. This role allows you to lead technical decisions and work on cutting-edge cloud-native infrastructure.

Details

5+ years of experience in ML systems
Location: Miami, in-office
Skills: Python, vLLM, SGLang, TensorRT-LLM, Kubernetes, AWS, GCP, Azure

The work

Push throughput through kernel-level tuning and continuous batching
Cut latency by profiling and fixing bottlenecks
Optimize KV cache utilization with advanced techniques
Quantize models without quality regression