Sripad Karne

I'm building a company in stealth in physical AI and on-device inference.

Alongside that, I do research at Columbia with Prof. Kostis Kaffes on optimizing edge AI inference.

Before this, I did independent research in AI Safety, Interpretability, and Physical AI, and worked on AgentOpt at DAPLab with Prof. Tianyi Peng and Dr. Wenyue Hua. I was also an AI Engineer Intern at IBM.

I'm a Master's student in Data Science at Columbia University, graduating December 2026. I did my undergrad at UC San Diego, studying Cognitive Science & ML, advised by Prof. Zhuowen Tu.

Blog · Personal · CV

Publications

Safety Monitors Mostly Catch What the Model Already Refuses

Sripad Karne

Under review at ICLR 2027 (main track)

How Far Do Auto-Interpretation Labels Generalize? A Controlled Study Across Languages, Scripts, and Rewordings

Sripad Karne

AACL-IJCNLP 2026 (main conference)

What the Guard Misses, the Robot Executes: Implied Harm in VLA Instructions

Sripad Karne and Arjun Balaji

Submitted to the Science of Physical AI Safety (SPAIS) Workshop @ CoRL 2026

Recall Is Not Protection: Evaluating Safety Monitors Against Model Compliance

Sripad Karne

JUDGe Workshop @ NeurIPS 2026 (poster)

One Language, Two Scripts: Probing Script-Invariance in LLM Concept Representations

Sripad Karne

Unifying Concept Representation Learning (UCRL) Workshop @ ICLR 2026

Which Model for Which Role? Cost-Aware Pareto Search over LLM Agent Configurations

Qian Xie, Wenyue Hua, Sripad Karne, Yueli He, Armaan Agrawal, Nikos Pagonas, Eugene Wu, Kostis Kaffes, Nairen Cao, and Tianyi Peng

Resource-Aware Agentic AI (RAAAI) Workshop @ NeurIPS 2026

Wenyue Hua, Sripad Karne, Qian Xie, Armaan Agrawal, Nikos Pagonas, Kostis Kaffes, and Tianyi Peng

Technical report, arXiv 2026

A framework-agnostic optimization layer for client-side model selection in multi-agent LLM systems, released as an installable package.

Machine Learning–Predicted Risk Trajectories for Incident Chronic Kidney Disease and Associations with Post-CKD Outcomes

Aaron Boussina, Amy M. Sitapati, Soo-Young Yoon, Sripad Karne, Jongwoo Seo, Woo-jung Kim, and Hyeon Seok Hwang

Journal of Medical Systems, 2026

Experience

Founder, Stealth Startup

Sep 2026 – Present · San Francisco

Graduate Researcher, ML Systems, Columbia University

Sep 2026 – Present · Advised by Prof. Kostis Kaffes

Optimizing LLM inference for edge hardware.

Visiting Member, FAR.AI

Fall 2026 · Berkeley

AI Engineer Intern, IBM

May 2026 – Aug 2026 · San Francisco

Graduate Researcher, Agentic AI Systems, DAPLab, Columbia University

Jan 2026 – Jun 2026 · Advised by Prof. Tianyi Peng & Dr. Wenyue Hua

Optimizing agentic AI infrastructure.

Biomedical AI Intern, UC San Diego Health

May 2025 – Oct 2025 · Advised by Prof. Aaron Boussina

Awards

NVIDIA & Dell GB10 Agentic AI Hackathon — 1st place, Agentic AI Track. Code
- Won against 40 competitors from 600+ applicants.
- Built Guardian AI, a real-time multi-video agentic analysis system for warehouse safety.
BlueDot Impact Rapid Grant ($3,000)

Contact

Email: sk5695 [at] columbia [dot] edu
LinkedIn · Google Scholar · GitHub