Neeraj Venna

AI Fellow · San Francisco, California

Evaluated agentic memory through temporal recall, conflicting information, irrelevant context, and paraphrased questions.

• Worked with Mem0 portfolio evaluation scenarios.
• Separated retrieval failures from reasoning failures when examining model responses.

AI Research Intern · La Jolla, California

Built behavioral analysis and pose quality tools for ALS research.

• Used PyTorch, OpenCV, NumPy, and pandas for pose analysis and quality control.
• Used Docker, multiprocessing, and SLURM for computational research.

Research Assistant · La Jolla, California

Supported brainstem interoception research through two-photon imaging and neuronal-region analysis.

• Worked with two-photon imaging data and region-of-interest analysis.
• Used Cellpose and FIJI for neuron segmentation and image analysis.

Data Engineer Intern · New Brunswick, New Jersey

Built data tools and application components for incident-report analysis and geospatial analysis.

• Worked across React, FastAPI, and PostgreSQL application components.
• Used scikit-learn, spaCy, pandas, and GeoPandas for NLP and geospatial analysis.

BeliefSpec ↗

A controlled study of whether next-observation prediction helps recurrent memory retain information for a later decision.

Python / PyTorch / MiniGrid / NumPy

Black Hole Simulation ↗

A C++ exploration of Schwarzschild ray tracing, numerical integration, and the visual language of gravitational lensing.

C++17 / OpenGL / GLSL / GLUT

Converge ↗

TypeScript / Node.js / Git / Next.js / pnpm

90 / 90 / 1 ↗

Flutter / Dart / Riverpod / Drift / SQLite