01
Generative AI & LLMs
Architecting autonomous agent networks and semantic retrieval pipelines using state-of-the-art open-source and proprietary foundation models.
- Fine-tuning models using QLoRA, LoRA, and PEFT techniques
- Orchestration via LangGraph, LangChain, and LlamaIndex frameworks
- Vector database engineering (Pinecone, Milvus, Qdrant, pgvector)
- Advanced hybrid RAG (Retrieval-Augmented Generation) pipelines
- Evaluations, safety frameworks, and model guardrails (Guardrails AI)