AI Engineering Webinars
Live technical teardowns, live coding sessions, and Q&A workshops hosted by Founder & Principal AI Architect Umar Abbas and Esaholic engineers. Gain deep engineering insights into RAG performance tuning, LangGraph agent design, vector indexing, and private VPC vLLM cluster deployment.
Building Low-Latency Enterprise RAG with pgvector & Cohere Rerank
Join Founder & Principal AI Architect Umar Abbas for a 90-minute hands-on engineering session. We will write live SQL migrations for pgvector HNSW indexing, benchmark Reciprocal Rank Fusion (RRF) search, and configure cross-encoder reranking microservices.
On-Demand Webinar Recordings
vLLM Cluster Optimization Teardown
Deep-dive into PagedAttention KV cache configuration, AWQ 4-bit quantization benchmarks, and GPU VRAM utilization tuning.
LangGraph Checkpointers & Human-in-the-Loop
Step-by-step walkthrough of setting up PostgresSaver state checkpointers and configuring manual approval interrupts in agent swarms.