Kayvan Zahiri — AI Engineer & Software Developer

About Me

I'm an AI Engineer and Software Developer with a passion for building intelligent systems that make a real impact. Currently working on the Voice AI team at Asurion, I bring experience across the full AI/ML lifecycle — from training and fine-tuning LLMs to deploying production-grade data pipelines.

With a B.S. in Computer Science and currently pursuing an M.S. in Data Science & AI at the University of San Francisco, I combine deep technical knowledge with practical engineering skills. I love crafting full-stack applications powered by cutting-edge AI.

AI / ML

LLM fine-tuning, RLHF, RAG, prompt engineering, and model evaluation

Full-Stack

React, TypeScript, Java, Python — building apps from database to deployment

Cloud & Data

AWS & GCP certified, ETL pipelines, distributed computing, Docker

Experience

AI Engineer

Asurion

Jan 2026 — Present Remote

Member of the Voice AI team, building conversational AI solutions

AI Engineer

Spotly Jobs

Oct 2025 — Jan 2026 Remote

Built optimized ATS pipelines, increasing job coverage 5%+ and processing hundreds of postings per run via dlt/dbt
Created 7 Dagster assets/sensors to automate ETL workflows, reducing manual intervention 50%+
Improved processing speed by 30–40% through optimized scraping logic and API handling

AI Engineer

Outlier AI

May 2024 — Sep 2025 Remote

Trained LLMs using RLHF, improving instruction-following accuracy by 20%
Evaluated 1M+ tokens across multiple datasets, surfacing 300+ instruction-following errors
Refactored 3+ AI models to generate more precise and succinct output

Software Developer

University of San Francisco · IDEA Team

Sep 2024 — May 2025 San Francisco, CA

Lead developer delivering 3 full-cycle applications for the IDEA team
Created 3 GenAI Python apps adopted by 50+ students and professors
Researched and evaluated 10+ existing AI tools and technologies

Software Developer

Founders Network

Aug 2024 — Dec 2024 San Francisco, CA

Built Slack integrations into a codebase of over 10,000 lines of code
Delivered 8 sprint cycles in Agile with a 95% on-time delivery rate
Collaborated directly with the CEO and a team of professional developers

Software Developer

University of San Francisco

May 2024 — Aug 2024 San Francisco, CA

Created and deployed 2 generative AI Thunkable apps, one featured on the site's front page
Lead developer on a full-stack PeopleMuseum project — 5,000+ lines of code
Built front-end UI with React JS, achieving load times under 2 seconds

Featured Projects

Mobile App AI

PantrIQ

Full-stack AI-powered mobile app for smart pantry management with recipe suggestions, automated meal planning, shopping list generation, and multi-input support (scan, voice, text).

React Native TypeScript Supabase OpenAI TailwindCSS

App Store

Python Library Open Source

PeopleCodeOpenAI

Python library providing easy access to OpenAI's tools and APIs — including text-to-speech, speech recognition, and RAG. Used in introductory courses at USF.

Python OpenAI API RAG Speech Recognition

Live Site

Full-Stack Java

Search Engine

Full-stack search engine with inverted index, TF-IDF ranking, and multithreaded web crawler. Built with 3,600+ lines of code including comprehensive Javadoc documentation.

Java 21 Apache OpenNLP Jetty Bootstrap Maven

GitHub

Data Science Streamlit

Semiparametric Regression Visualizer

Interactive web app for exploring semiparametric regression models. Compare OLS vs Generalized Additive Models with real-time visualizations on datasets like Boston Housing and World Happiness.

Python Streamlit pygam statsmodels Google Cloud Run

Live App

GenAI Research

AI Interviewer Tool

GenAI-powered research app that simulates user interviews and focus groups. Define participant personas, conduct interactive interviews, and gather AI-driven insights for product and UX research.

Python Streamlit OpenAI Prompt Engineering

Live App

Data Dashboard NLP

AI/ML Industry Data Dashboard

Data dashboard aggregating AI/ML content from arXiv papers and Medium articles. Features automated scraping via GCS, article trend visualizations, and Anthropic topic clustering analysis.

Python Streamlit GCS NLP Google Cloud Run

Live App

Skills & Technologies

Languages

Python Java C SQL TypeScript JavaScript HTML/CSS

AI / ML

Generative AI LLM Fine-Tuning RLHF Prompt Engineering Model Evaluation RAG OpenAI Claude PyTorch

Data Science

PySpark Pandas NumPy Matplotlib Plotly ETL Pipelines

Tools & Platforms

AWS GCP Docker Git / GitHub Bash Dagster MongoDB Distributed Computing

Frameworks

React / React Native Supabase TailwindCSS Bootstrap Eclipse Jetty Maven Streamlit

Education & Certifications

M.S. in Data Science & Artificial Intelligence

University of San Francisco

Jul 2025 — Jul 2026 (Expected)

B.S. in Computer Science

University of San Francisco

Aug 2021 — May 2025

AWS Certified Cloud Practitioner

Amazon Web Services

Google Cloud Digital Leader

Google Cloud

Let's Connect

I'm always open to new opportunities, collaborations, and conversations. Feel free to reach out!

kzahiri@dons.usfca.edu LinkedIn GitHub