Ranjitha Kulkarni builds intelligent systems that hold up in production. As a Staff Machine Learning Engineer at NeuBird.ai, she works on agentic AI, covering the practical ingredients that make agents reliable: selecting and integrating tools, designing effective retrieval pipelines, and defining evaluation metrics that capture real assistant behavior.

Her track record spans some of the most demanding applied AI domains. At Dropbox, she built LLM- and agent-powered product capabilities for Dropbox Dash. Before that, at Microsoft, she worked on speech recognition, language modeling, online metrics, and the evaluation of intelligent assistants. Her publications include voice query reformulation and automatic online evaluation of intelligent assistants, and her patents include automated closed captioning using temporal data and hyperarticulation detection.

Ranjitha holds a master’s degree from the Language Technologies Institute at Carnegie Mellon University, a research grounding that continues to inform her engineering work on agents, retrieval, and evaluation.