Professional Header & Bio
Jahnavi Kachhia is a global AI and machine learning leader with 10+ years of experience building scalable, production-grade systems that serve millions of users across healthcare and consumer platforms. She specializes in translating advanced AI research into real-world impact, with expertise in generative AI, predictive systems, and end-to-end ML infrastructure.
Her work focuses on designing reliable, explainable AI for safety-critical environments, including large-scale, real-time systems where performance and trust are essential. She has contributed to AI platforms deployed globally, operating at scale in user-facing and clinical contexts.
Jahnavi's research includes peer-reviewed publications across IEEE and international venues, with 174 citations across domains such as biomedical AI, brain-computer interfaces, and applied machine learning. She is also an active open-source contributor, with projects achieving 152 GitHub forks and 154K Docker downloads, reflecting strong global adoption.
Pioneering Research & Original Contributions
Meta Ray-Ban AI
Pioneered AI logic for multi-modal reminders, setting a new industry standard for wearable intelligence.
Significance Statement: Helped translate multimodal AI from prototype concepts into consumer-facing intelligent assistance, contributing to product behavior that made contextual memory and visual tracking tangible at scale.
Healthcare AI: ICU Early Risk Predictor
Developed an open-source framework (Dockerized) for predictive clinical risk assessment, utilized by researchers worldwide.
Significance Statement: Advanced reproducible healthcare AI by packaging clinical prediction workflows into accessible infrastructure that supports experimentation, validation, and downstream medical research translation.
Radar Signal Analysis
Established novel deep learning architectures for signal deinterleaving in high-density environments.
Significance Statement: Extended deep learning techniques into complex signal environments where robust separation and interpretation are essential for mission-critical analysis.
Professional Profiles and Public Visibility
- Google Scholar - citation record, publication visibility, and scholarly profile
- GitHub - code repositories, project visibility, and technical portfolio
- Docker Hub - published containers and applied machine learning artifact visibility
- Kaggle - dataset visibility, competitions profile, and Dataset Master ranking
- Academia.edu - academic affiliation and publication visibility
- LinkedIn - professional profile, speaking visibility, and career-facing public presence
- ResearchGate - academic profile visibility and research discovery
- ORCID - persistent researcher identity and scholarly record linkage
Global Peer Review & Technical Judging
Dedicated to ensuring technical excellence and ethical standards in the global AI ecosystem through the rigorous evaluation of emerging research and technologies.
Conference Program Committees
- Expert Jury: IJCAI 2025
- Expert Jury: IJCAI 2026
- Expert Jury: AAAI 2025 workshops and review tracks
- PAKDD 2026
- Editor: PLOS ONE
Innovation Panels
- Expert Jury: MIT Hacking Medicine
- Expert Jury: Eurekathon
- Expert Jury: AI for Connectivity
- Expert Jury: Nexora Hacks 2026
Public Engagements & Expert Insights
AI as a Medical Co-Pilot
Invited to share insights on LLM interpretability for clinical decision support systems.
Media Mentions
Industry Commentary & Analysis
- All Tech Magazine: AI That Doesnt Collapse Under Pressure
- The Verge: Meta's Ray-Ban will now remember for you
- Gizmodo: Ray-Ban Meta Smart Glasses and reminder features
- TechCrunch: Meta updates Ray-Ban smart glasses
- USA Today: Meta Ray-Ban smart glasses live translation