Basem Rizk

Applied AI Engineer & Researcher

Pro, and to be more pro by the time. Just need to imagine ✨

My Resume
GitHub
Scroll to explore

Experience

Jan 2026 – Present · San Francisco, CA

Applied AI Engineer

CodeRabbit
June 2024 – Jan 2026 · San Ramon, CA

AI Engineer

Redblock
  • Led the development from the ground-up of on-premise Agentic AI solution to automate reliably identity tasks of any web application lying between computer-use and RPA.
  • Achieved with my agent 28%+ better than the top-performing competitor agents on in-house identity tasks benchmark, with a remarkable 0% fault rates.
  • Built pre-liminary agent to explore the available features in web-apps and automate repetitive tasks in SAS Applications.
  • Filed a number of provisional patents for methodology, novel approach as well as use cases in the domain.
May 2023 – May 2024

AI/ML Research Scientist

Learning Sciences Lab, Institute for Creative Technologies (ICT)
  • Crafted an optimized pipeline for video content analysis and understanding, fusing 10+ CV and NLP methods ranging from Sentence Segmentation and Key-Frame Selection to Dense Captioning and Graph Construction (PI. Dr. Ben Nye).
  • Built downstream task heads on top of the pipeline for tasks such as Video Type Classification, Competencies Detection, and Multi-modal Reference-based Prompting.
  • Designed an algorithm to query database of videos and interactively inject new domain-specific knowledge employing knowledge graphs on the basis of lexical databases.
Dec 2022 – May 2024

NLP Research Assistant

CUTE LAB NAME, NLP Group, Information Sciences Institute (ISI)
  • Investigated companion bots for tracking Python notebook development using large language models (LLMs) and improved quality of generated corresponding question-answer pairs by 80%. (PI. Dr. Jonathan May and Dr. Jay Pujara).
  • Built with team of 3, an LLM-based moderator agent that persuades users to apply non-violent communication strategies through DARPA Civil Sanctuary applied research (PI. Dr. Jonathan May and Dr. Kristina Lerman).
  • Designed and developed a configurable dynamic prompting framework that allows hooking up endpoints and APIs.
Jan 2022 – June 2023

AI/ML Lead

NASA S.U.I.T.S Challenge, Team AEGIS (USC/UA, USC/UCBerkeley)
  • Led AI division to construct off-cloud Digital Assistant on local server, communicating with Microsoft Hololens 2, playing Augmented Reality (AR) solution to reduce cognitive load and fatigue of astronauts throughout procedures on EVA missions.
  • Architected and implemented a client-agnostic framework employing open-source libraries for speech-to-text, dialogue management, and text-to-speech.
  • Received great feedback from experts' trials on the Rock Yard Site at Johnson Space Center and from a panel of astronauts.
May 2022 – Jul 2022 · Marina Del Rey, CA

Founding Software Engineer Intern (AI/ML Oriented)

TadHealth
  • Devised starting blocks and outlined System Specifications Requirements (SRS) for future blocks of confidential AI-powered system, including an extensible web-scraping component, database management system, and NLP-oriented controller.
May 2022 – Jul 2022

Computer Vision Research Assistant

Signal Analysis and Interpretation Lab (SAIL), USC
  • Leveraged attention and pose detection libraries to enable analysis in 300+ videos of interactions between potential autistic kids and caregivers.
Sep 2020 – Jul 2021

Teacher Assistant (Adjunct Lecturer)

GUC, Egypt
  • Taught the practical sessions to students and graded assessments in Constraint Programming (Graduate Course) and as part of a team, in Software Engineering Lab and Advanced Databases courses.
  • Expanded curriculum by adding Google OR-Tools, designed final project, and supervised students during implementation.
Mar 2019 – Jun 2019

Speech Recognition Research Intern

Institute for Information Systems, Germany
  • Compiled and evaluated ASR on a number of machine architectures while studying underlying ML models' architectures.
  • Trained FB Wav2Letter model, from scratch, achieving 79% accuracy on LibriSpeech other-test dataset.
  • Investigated performance and compared against previous data by the institute through a bachelor thesis titled "Evaluation of State of Art ASR Engines with Local Inferencing," selecting the institute's ASR system choice for the smart speaker project.
  • Gained 23+ citations (including Amazon Alexa and Meta AI Research) per followed conference paper and resulting thesis.
13 Provisional Patents Filed

Featured Research

Estuary: A Framework For Building Multimodal Low-Latency Real-Time Socially Interactive Agents

ACM IVA '24 CHI '25 Case Study

A framework for building multi-modal agents that perceive, reason about, and respond to social cues in real-time human interactions. Estuary integrates vision, language, and behavioral models into a unified architecture for socially aware AI.

ACM DL Google Scholar arXiv

Publications

From Videos to Knowledge Graphs — Framework to Marry Methods for Multimodal Content Analysis and Understanding

Basem Rizk, Joel Walsh, Mark Core, and Benjamin Nye

arXiv:2510.01513v1 · April 2024
Optimizing SIA Development: A Case Study in User-Centered Design for Estuary, a Multimodal Socially Interactive Agent Framework

Spencer Lin, Miru Jun*, Basem Rizk*, Karen Shieh, Scott Fisher, and Sharon Mozgai

CHI EA '25 Extended Abstracts 2025 · Oct 2024
Beyond Visual Understanding: Introducing PARROT-360V for Vision Language Model Benchmarking

Harsha Vardhan Khurdula, Basem Rizk, and Indus Khaitan

COLING Industry Track Proceedings 2025 · Oct 2024
PARROT: Performance Assessment of Reasoning and Responses On Trivia for LLM Benchmarking

Harsha Vardhan Khurdula*, Basem Rizk*, Indus Khaitan, Aviral Srivastava, and Rajvardhan Khaitan

Preprint · Oct 2024
Estuary: A Framework For Building Multimodal Low-Latency Real-Time Socially Interactive Agents

Spencer Lin*, Basem Rizk*, Miru Jun*, Andy Artze, Caitlin Sullivan, Sharon Mozgai, and Scott Fisher

ACM IVA Demos 2024 · July 2024
Scalable Conversational Moderation: Promoting Constructive Dialogue to Reduce Online Polarization

Hyundong Cho, Shuai Liu, Taiwei Shi, Darpan Jain, Basem Rizk, Yuyang Huang, Zixun Lu, Nuan Wen, Jonathan Gratch, Emilio Ferrera, and Jonathan May

NAACL 2024 · Feb 2024
Alzheimer's Disease Classification Using Volume Correlations and Multi-Atlas Spatio-Contextual Graph Isomorphism Networks

Basem Rizk, Anthony Guerra, Rohit Penumarti, and Ajitesh Srivastava

Submitted in ICASSP 2026 · May 2023
Open Source Speech Recognition on Edge Devices

René Peinl*, Basem Rizk*, and Robert Szabad

ACIT'2020 & IEEE Xplore · Sep 2020
Evaluation of state-of-the-art open-source ASR engines with local inferencing

Basem Rizk (Thesis)

GUC Thesis Journal 2020 · Aug 2019

Projects

Alzheimer's Disease (AD) Classification

2023
  • Achieved SOTA competitive results with 74.8% recall by novel approach of considering volume correlations with multi-atlas spatio-contextual GINs in 3-way AD from structural MRI images classification on ADNI dataset split.
Emotion Recognition Per Context Modeling Reproduction Study 2022
  • Reproduced (Lee and Lee, 2021) work as part of a team of 2 to detect emotions in conversations, employing pre-trained language models without requiring structured knowledge bases.
  • Generated 20% of 2 datasets based on English-Arabic subtitles alignment and showed comparable accuracies of both to English datasets in evaluation.
Dependency Trees Parsing Using Neural Networks 2022
  • Reproduced (Chen et al., 2014) with ARC-Standard and ARC-Eager transition-based parsing with PyTorch on CoNLL data and experimented with learning word embeddings.
Constrained Compensation System for GUC 2019
  • Ranked best project in class, modeled as Constraint Satisfaction Problem (CSP) in Prolog CLPFD, interfacing with Django API.
  • Architected as model engine and query formatter. SQL tables are created, then Prolog queries are formatted and issued.

Education

Master of Science

Computer Science (Artificial Intelligence)

University of Southern California (USC) →
Aug 2021 – Dec 2023 · GPA: 3.76
Dean's Scholarship
Theory of Machine Learning (PhD) Deep Learning and Its Applications ML Apps for Medical Data (PhD) Advanced NLP (PhD) Machine Learning Analysis of Algorithms Foundations of AI Web Technologies

5-Year Bachelor of Engineering

Computer Science and Engineering

German University in Cairo (GUC) → Course details
Sep 2015 – Aug 2020 · GPA: 3.9 "High Honors"
Machine Learning Rule-based and Constraint Programming Computer Vision Computer Security Intro to Biomed Engineering Intro to Deep Learning with Self-driving cars Game-dev in Unity Affective Computing Seminar

Skills & Leadership

Languages

PythonJavaProlog/CHRJavascript/TSC#C/C++SQLHaskell/LambdaSystem VerilogAssemblyBash

Frameworks & Tools

PytorchScikit-LearnTensorflow/KerasNumpyPandasTransformersScrapyAndroidUnityNodeJsCLPFDSlurm/HPC

Leadership

Viterbi Grad Leader — DirectorUSC MENA Student Assembly — FounderGUC Speech Club — HeadINSIDER GUC News & Reporting CommitteeAI/ML Division Lead, Team AEGIS (USC/UCBerkeley) NASA SUITS