tarun gunuguntla

I’m an AI and Data Science professional focused on building production-ready Generative AI solutions—especially LLM agents, RAG systems, and automation pipelines—that integrate with enterprise systems and drive measurable business impact.

At Haiva Inc as Member Technical Staff (Founding Engineer), I built scalable backend systems, agentic layers, and LLM pipelines powering adaptive AI agents and enterprise automations. I designed and orchestrated multi-agent systems across tasks and APIs, and I delivered real-time, multilingual voice AI agents integrating cloud TTS/STT and telephony workflows via Twilio Streams and WebSockets.

I also partner directly with clients to identify high-impact AI use cases, define solution architectures, and deliver end-to-end implementations. Leading requirement gathering, technical discussions, and iterative feedback cycles helped improve adoption and delivery efficiency.

Earlier, as an SDE Intern at Linx Works, I engineered a conversational AI analytics assistant with NL-to-insights workflows across web and mobile platforms. I built NLP pipelines using Python and transformer models for NL-to-SQL, developed a multi-dialect query engine for PostgreSQL, MySQL, and BigQuery, and created SAIL (Structured API Integration Language) with LLM support (OpenAI GPT-3.5, Vertex AI) and a Blockly-based interface.