Prateek Chhikara

Applied AI engineer · San Francisco

Prateek Chhikara.

I turn real-world problems into AI systems that work beyond the demo.

I’m an Applied AI Engineer at Mistral AI, working directly with clients to solve industry use cases with AI and machine learning.

Previously, I was a founding AI engineer at Mem0 and a researcher at USC’s Information Sciences Institute. I’m interested in how we make models more reliable, more perceptive, and better at remembering what matters.

Prateek Chhikara
Engineer. Researcher. Artist.
25+ publications 2,500+ citations 5+ years building AI MS Computer Science, USC

Selected research

All publications
  1. TMLR · 2025

    Mind the confidence gap: Overconfidence, calibration, and distractor effects in Large Language Models

    Understanding and reducing overconfidence in large language models.

  2. ECAI · 2025

    Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

    Scalable long-term memory for production AI agents.

  3. ICLR · 2025

    MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs

    Helping multimodal models perceive small visual details without retraining.

Latest writing

All writing
  1. When There’s No Ground Truth for Evaluation

  2. Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models

  3. Reaching 1,000 Citations: My Research Journey

Outside the terminal

I draw anime-inspired artwork and write about life, research, and the things I learn along the way. Visit the sketchbook