Product engineer - ai infrastructure
UdaipurKatonic AI
...inference time Your Responsibilities Learn to deploy and test LLM serving infrastructure (v LLM, SGLang, NIM) Test fine-tuning pipelines - Lo RA, QLo RA, and full fine-tuning workflows Run benchmarks - measure latency, throughput, memory usage, fine-tuning time Validate new models before production (LLa MA, Mistral, Deep Seek) [...]
Category IT & Telecommunications
15 days ago in Labor24