Hello, I'm

Moeen Bagheri

AI Engineer

Agentic Coding, LangGraph, Evaluation, AI Agents

Toronto, ON, Canada
Download Resume Download CV

About Me

AI Engineer with 8+ years of professional experience and 3+ years building production LLM agents and enterprise AI systems. Lead developer of BASF's Talk2Data, a module within FOX, with 7,000+ users. Winner of BASF's 2025 Digital Award and 2026 ICV Albrecht Deyhle Award for Controlling Excellence. Specializing in agentic workflows, evaluation frameworks, and LangGraph architectures that ship reliable AI products at scale.
Email LinkedIn GitHub Toronto, ON, Canada

Skills & Expertise

Concepts

Agentic Coding Multi-Agent Orchestration AI Agent Design & Development Agent Tool Design Fullstack & API Development Evaluation & Testing CI/CD RAG Time-Series Forecasting Fine-tuning Transfer Learning Computer Vision NLP

Soft Skills

Technical Leadership & Mentorship Stakeholder Communication

Languages

Python SQL JavaScript C# R

Tools & Frameworks

LangChain/LangGraph Databricks MLflow DevOps GitHub Copilot Cursor Claude Code MCP Docker Kubernetes Git PostgreSQL Pandas NumPy PySpark PyTorch TensorFlow LightGBM Scikit-learn HuggingFace OpenAI API Azure Flask FastAPI
AI Engineer & Lead Developer thumbnail AI Engineer & Lead Developer
AI Engineer & Lead Developer
BASF
Toronto, ON, Canada | Oct 2024 - Present

Lead developer of Talk2Data, the data assistant within BASF's FOX platform. Winner of BASF's 2025 Digital Award and ICV Albrecht Deyhle Award for Controlling Excellence 2026.

Technical Leadership & Mentorship Fullstack & API Development Evaluation & Testing Stakeholder Communication Python
  • Natural Language to SQL: Built a LangGraph agent with MLflow tracing that answers questions using Databricks SQL and RAG, returning tables, charts, and analysis. Supports new data sources through configuration.
  • Executive Briefing: Built a monthly briefing for finance leadership that used deterministic analysis to find KPI changes and drivers, an LLM to explain results in natural language, with grounding to ensure all findings are backed by evidence.
  • Website Assistant: Implemented an agent to work within a website with Power BI reports and answer based on what the user sees on their screen.
  • Evaluation: Built a framework to evaluate SQL accuracy, latency, and tool calls to catch regressions before release.
  • Dashboard Automation: Built a GitHub Copilot multi-agent system to automate the process of Power BI report creation from intake files, with validation to ensure data and layout reliability. Onboarded BI developers new to coding agents.
  • Agentic Coding: Built workflows in GitHub Copilot and Cursor to implement features, run tests and evaluations, review changes, and open pull requests across multiple repositories, with access to Microsoft Teams messages and meetings, Outlook emails, and Azure DevOps to gather necessary context, and a self-enhancing loop to improve itself over time.
  • Developer Acceleration: Defined how to improve developer productivity and enable coding agents within BASF's company-wide AI program to help development teams turn ideas into working prototypes faster.
Founder & AI Engineer thumbnail Founder & AI Engineer
Founder & AI Engineer
YT Copilot
Toronto, ON, Canada | Sep 2023 - Oct 2024

Built an AI Chrome extension app called YT Copilot to work inside YouTube.

Fullstack & API Development Evaluation & Testing Python JavaScript MLflow
  • YouTube Assistant: Developed an AI agent for YouTube that summarized videos, organized content into chapters, answered questions about videos, conducted semantic searches, and identified promotional segments and interruptions. Implemented chunking and aggregation to process long videos.
  • Fullstack Development: Developed the JavaScript frontend integrated with YouTube's UI, the Flask / PostgreSQL backend deployed on Azure Kubernetes Service (AKS) with Docker, Ory Kratos authentication, and Stripe billing.
  • Fine-tuning & Optimization: Improved the quality and reliability of the responses using fine-tuning, distillation, and prompt engineering techniques.
Machine Learning Engineer thumbnail Machine Learning Engineer
Machine Learning Engineer
Super GeoAI Technology Inc.
Toronto, ON, Canada | Jan 2022 - Jul 2023

Led a team of 7+ engineers developing computer vision models for agriculture.

Technical Leadership & Mentorship Fullstack & API Development Evaluation & Testing Stakeholder Communication Python
  • Computer Vision: Built object detection models in PyTorch and TensorFlow that graded seeds and estimated crop yield from photos taken with phones and drones. Increased efficiency by over 80% for the agricultural partners.
  • Model Enhancement: Improved accuracy by 10% for seed grading and 15% for wheat head detection by fine-tuning models pre-trained on COCO and Pascal VOC and tuning hyperparameters with Ray Tune.
  • System Design: Deployed the models with a Flask backend and a JavaScript frontend, integrated with a NextCloud-based storage platform and Ory Kratos for authentication.
  • Leadership: Conducted technical interviews, team meetings, and code reviews.
Machine Learning Researcher (Doctoral Research) thumbnail Machine Learning Researcher (Doctoral Research)
Machine Learning Researcher (Doctoral Research)
IBM
Toronto, ON, Canada | Jul 2021 - Jan 2022

NLP and transformer research to find conflicting or duplicated entries in SRS documents.

Python Git Pandas NumPy PyTorch
  • NLP: Built BERT-based models in PyTorch and HuggingFace to detect conflicting and duplicate requirements in Software Requirements Specification (SRS) documents.
  • Model Optimization: Improved F1-score by 20% compared to the baseline by fine-tuning a Microsoft pre-trained model.
Teaching Assistant - Practical Deep Learning (CIND850) thumbnail Teaching Assistant - Practical Deep Learning (CIND850) thumbnail
Teaching Assistant - Practical Deep Learning (CIND850)
Ryerson University
Toronto, ON, Canada | Sep 2021 - Dec 2021

Taught Practical Deep Learning (CIND850) to graduate students.

Technical Leadership & Mentorship Python Pandas NumPy PyTorch
  • Mentorship: Delivered deep learning lectures and tutorials and mentored 20+ graduate students on model design and implementation.
  • Assessment: Graded assignments and exams, and gave students feedback on their deep learning implementations.
  • Curriculum Development: Designed the lab exercises and their solutions, with a focus on practical uses of deep learning.
Quantitative Data Scientist thumbnail Quantitative Data Scientist thumbnail
Quantitative Data Scientist
Electronica AI
Toronto, ON, Canada | Jun 2014 - Aug 2018

Built trading algorithms as a contractor throughout university.

Fullstack & API Development Evaluation & Testing Stakeholder Communication Python C#
  • Trading Algorithm Development: Worked with 5+ engineers to design and develop high-frequency trading algorithms with a daily order flow of $10M+, and used machine learning to improve their predictive accuracy.