Python, LangGraph, Building pipelines for structured and unstructured data, Vector databases, Multi-agent systems

pipelining , Gpu, Pytorch, Kubernetes, Python, LLM inference orchestration, NVIDIA Dynamo, edge AI chips, llm-d, NVIDIA DGX, infiniband, model optimization techniques, GPU infrastructure, RoCE networking, storage for AI workloads, KV-cache-aware systems, hardware acceleration, vLLM, NPU, disaggregated serving, NVLink, quantization

state management , Python, LangGraph, Observability frameworks, Evaluation pipelines, Vector databases, RAG-like architectures, Multi-agent systems, Granular tracing, LLM-native metrics, CrewAI ADK

Javascript, Python, AI LLM systems