GNANI INNOVATIONS PRIVATE LIMITED
Gnani.ai - LLMOps Engineer
- Hybrid
... LLM serving stack across vLLM, SGLang, and NVIDIA Dynamo - including engine selection per workload, with benchmark evidence to justify it- Tune the serving path end to end: continuous batching, chunked prefill, paged and radix attention, prefix and KV caching, cache-aware and sticky routing, speculative decode integration- ...
Bangalore, भारत