Mohammad Abdollahi

MOHAMMAD ABDOLLAHI

ML Engineer | Research Scientist | Agentic AI | NLP & LLMs | MLOps Specialist

Bridge Research and Production. Optimize. Deploy.

INITIALIZE_CONTACT VIEW_SYSTEM_LOGS

01. SYSTEM_OVERVIEW

I am a Machine Learning Engineer and Researcher with 6+ years of experience in Machine Learning, Natural Language Processing (NLP), Large Language Models (LLMs), Agentic AI and MLOps. Currently, I am pursuing my graduate studies at York University (Toronto, Canada) under the supervision of Prof. Hadi Hemmati (Google).


My research focuses on LLM Reasoning and Agentic AI within the realm of Software Engineering. In simple terms, I work on the theoretical foundations of AI to build intelligent, autonomous coding agents capable of solving complex software tasks.


I specialize in designing scalable, end-to-end ML systems that bridge the gap between research and production environments. I don't just train models; I challenge them. My passion lies in the edge cases and the 'impossible' problems where standard algorithms fail, pushing the code beyond its current frontiers.

02. EXECUTION_HISTORY

Sep 2025 - Jan 2026

Machine Learning Engineer

Arteria AI | Toronto, CA

  • Developed an end-to-end RAG system using DeBERTa and vector search for legal docs.
  • Optimized Docker images, cutting size by 50% and accelerating build times by 70%.
  • Refactored and productionized ML products, ensuring CI/CD reliability.
Dec 2021 - Dec 2024

Machine Learning Engineer

Digikala.com

  • Redesigned RecSys using ViT + BERT & HNSW, boosting conversion by 72%.
  • Designed Uplift-Prediction tool increasing gross sales of daily deals by 39%.
  • Implemented LLM POCs using OpenAI API and Open Source models.
May 2021 - Dec 2021

Data Scientist

Snappfood

  • Developed Sentiment Analysis system achieving 89% accuracy on noisy labels.
  • Enhanced food categorization accuracy by 13% using fuzzy matching.
Jul 2019 - Aug 2020

Software Engineer

Virgool

  • Built a Persian text classifier (90% accuracy) and Spam Detection system (94% precision).

03. INSTALLED_MODULES

Languages

Python Go C/C++ Java JavaScript R

ML & AI

PyTorch TensorFlow HuggingFace OpenAI LangChain LangGraph Scikit-learn XGBoost Agentic AI RAG vLLM Ollama LMCache

Infrastructure & MLOps

Docker Kubernetes AWS GCP Kafka AirFlow MLFlow RabbitMQ Celery Databricks

Data & Backend

PostgreSQL MySQL MongoDB Redis Elasticsearch Qdrant GraphQL FastAPI Django

04. OUTPUT_DATA

Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulation. Mohammad Abdollahi et al.
Surveying the Benchmarking Landscape of Large Language Models in Code Intelligence. Mohammad Abdollahi et al.
Deep-Bench: Deep Learning Benchmark Dataset for Code Generation. Alireza Daghighfarsoodeh... Mohammad Abdollahi et al.
ComplexMatrixComb: Predicting Drug Combination IC50 Doses via Complex Numbers and Matrix Factorization. Mohammad Abdollahi et al.
ACCESS_GOOGLE_SCHOLAR

05. COMMUNITY_LOGS

Dec 2025 - Feb 2026

Program Committee & Reviewer

MSR 2026 | View Committee

  • Served as a Rapid Response Reviewer for the Mining Software Repositories conference (Top-tier SE venue).
  • Conducted thorough and high-quality peer reviews of research submissions under a tight timeline.
Mar 2021 - Apr 2021

Scientific Consultant

Datadays2021

  • Contributed to the design of a nationwide AI challenge focused on Learning to Rank (LTR) and Recommendation Systems.
May 2018 - Aug 2020

Board Member

IUT Computer Engineering Student Scientific Association (CESSA) | GitHub

  • Organized academic seminars, scientific presentations, and coding challenges to foster student engagement.
  • Facilitated workshops to deepen student understanding of computer engineering fields.