Senior ML Engineer | Kimchi (LLM Inference Optimization)
L’offerta in breve
Kimchi: Senior ML Engineer | Kimchi (LLM Inference Optimization). Lavoro da remoto internazionale, aperto a candidati in Italia. Livello: senior. Tecnologie indicate: Python, Postgres, Spark, AWS, GCP, Azure, Kubernetes, PyTorch, Hugging Face.
Responsabilità e requisiti sono riportati nel riepilogo editoriale qui sotto, nella lingua disponibile. Verifica i dettagli nell’annuncio dell’azienda prima di candidarti.
Sul ruolo
The Senior ML Engineer will improve production LLM inference across throughput, latency, and KV cache utilization. Kimchi matches workloads to cost-efficient models and serving configurations on customer infrastructure, accounting for traffic patterns, GPU hardware, memory, and quantization. The work spans inference engines such as vLLM, SGLang, and TensorRT-LLM, as well as distributed systems and multi-GPU deployments.
The engineer will profile and optimize serving performance, tune batching and kernels, measure quantization quality, and develop caching and cold-start improvements. The role also includes setting the technical direction for benchmarking and technology choices, then communicating decisions through writeups and reproducible experiments.
Highlights
- Optimize LLM throughput, latency, and KV cache use.
- Work across inference engines, GPUs, and distributed systems.
- Measure quantization tradeoffs on real workloads.
- Lead technical direction for inference optimization.
Questo recap è un riassunto editoriale di dataskew, non il testo dell'azienda.