Daniel Mehta

Applied AI Engineer • LLM Systems • APIs & Backend • Toronto

daniel.k.mehta@gmail.com LinkedIn GitHub

I build applied AI systems focused on LLM workflows, backend integration, retrieval and memory, and practical machine learning products. My background spans AI engineering, analytics, and full-stack technical work across startups, government, and internal tools.

Experience

Full-Stack & AI Intern - ArrowzSept 2025 - Feb 2026 • Remote
  • Built and integrated a machine learning-based sentiment analysis component for live chat conversations.
  • Designed and shipped a PostgreSQL-based persistent memory system for an LLM application using confidence and salience scoring.
  • Implemented memory processing features including PII filtering, episodic time normalization, semantic deduplication, and usage-based decay.
  • Integrated long-term memory into a live inference pipeline to enable context-aware responses across conversations.
  • Built automated testing and database cleanup workflows to improve system reliability.
  • Added backend authentication/security controls and integrated TTS/STT endpoints for voice-based AI interactions.
Data Analyst Intern - Ontario Ministry of EducationMay 2024 - Aug 2024 • Toronto
  • Optimized SQL- and VBA-based reporting workflows by improving inefficient query logic and data retrieval patterns.
  • Redesigned internal reporting interfaces using UX testing feedback and Figma mockups.
  • Translated policy and reporting requirements into reliable data workflows for operational analysis and decision-making.
Database Intern - DPCDSBMay 2023 - Aug 2023 • Mississauga
  • Designed and implemented an inventory management system for mechanical and electrical assets across 150+ buildings.
  • Improved data accessibility and operational reliability using the eBase platform.
  • Performed data validation and asset analysis to support accurate records and long-term facilities planning.
Data Research Specialist - MeterAug 2020 - Jan 2021 • Remote
  • Conducted structured lead research and data validation to improve database quality and reliability for sales and engagement workflows.

Education

MSc Artificial Intelligence - University of LiverpoolStarting May 2026 • Expected 2028
Graduate Certificate - AI with Machine Learning, Humber PolytechnicJan 2025 - Aug 2025 • Toronto

Dean's Honour Roll

BSc - Wilfrid Laurier University2020 - 2024 • Waterloo

Dean's Honour Roll 2021-2024

Skills

Python TypeScript SQL Go Julia PyTorch Scikit-learn TensorFlow Hugging Face LangChain LLM Pipelines Conversational Memory Systems FastAPI Flask REST APIs AWS PostgreSQL MongoDB Apache Spark

Featured projects

LLM + GNN Integration for Renewable Energy2025

Python, MoFlow, DimeNet++

  • Built a molecular innovation pipeline combining LLMs with graph neural networks for molecule generation and property prediction.
  • Led technical implementation across model integration and workflow development in an industry-sponsored capstone.

Project overview

Context-Aware Anime Recommender2025

Python, PyTorch, Streamlit, SASRec

  • Implemented a Transformer-based sequential recommender with feedback embeddings and genre-aware blending for personalized recommendation generation.
  • Built an interactive Streamlit demo with explainable recommendation outputs.

Repository

CooperLM-354M - Custom GPT-Style Language Model2025

Python, Hugging Face

  • Trained a 354M-parameter GPT-style language model on curated text datasets using the Hugging Face ecosystem.
  • Built and evaluated an end-to-end training pipeline for small-scale autoregressive text generation under limited compute constraints.

Model card

Salary Predictor - Multi-Language ML Pipeline2024

Julia, Go, Python, Bash, SQLite

  • Built a cross-language machine learning pipeline with model training, ETL, and a Go-based web interface.

Repository

BNART - Q-Learning for Urban Traffic2024

Python, Reinforcement Learning

  • Built a Q-learning traffic optimization project focused on improving routing and signal timing across large simulated scenarios.

Repository

Places

Highlighted countries I have visited. Count: 16.

List

Portugal (Azores), France, Germany, Iceland, Italy, Malta, Spain, Vatican City, Canada, United States, Mexico, Aruba, Bahamas, Barbados, Belize, Dominican Republic

Sketch

Draw then release to let it float.

Contact

Email daniel.k.mehta@gmail.com or message me on LinkedIn.