Jared Joselowitz
Bio
Jared Joselowitz is a research engineer at Ufonia, where Dora (an AI voice agent) makes clinical follow-up calls on the NHS and across US health systems. He builds the evaluation and hazard-analysis stack for clinical voice AI: multi-agent simulation, prompt-optimisation pipelines, and the audit infrastructure that has to hold up when there's a patient on the other end of the call.
Session (1)
Jared Joselowitz is a (senior) AI research engineer at Ufonia building and evaluating safety-critical clinical AI dialogue systems, with published work spanning LLM alignment (inverse RL), RAG evaluation metrics for clinical QA, multi-agent clinical conversation safety simulation, and ASR error impact in patient-facing conversations. Attending his session offers a rare practitioner perspective on where AI safety research meets live healthcare deployments.
Recent writing (5)
- Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning · paper · Oct 2025
- ASTRID - An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems · paper · Jul 2025
- MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation · paper · Aug 2025
- WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue · paper · Feb 2026
- Empathy as interactional accomplishment in clinical interactions with a conversational agent · paper · Mar 2026
Public activity researched automatically · as of Jun 2026