Siddarth Reddy Gurram

4+ years of work experience

Nov 20242 yrsPresent

Hyderabad, Telangana, India

- Led the end-to-end design and deployment of production Generative AI and LLM applications, building scalable RAG (Retrieval-Augmented Generation) pipelines covering document ingestion, parsing, chunking, embeddings, vector search, retrieval, and response generation. - Architected stateful AI agents using LangGraph / LangChain with tool calling, memory, and multi-step reasoning, alongside hybrid RAG + LoRA fine-tuned solutions for enterprise use cases, improving domain-specific accuracy and automation. - Deployed and optimized open-source LLMs with vLLM for on-prem inference, orchestrated multi-provider LLM / VLM routing with OpenRouter, implemented Langfuse observability and evaluation pipelines, and integrated NVIDIA NIM microservices for real-time speech-driven interactions.