CV

Education

• University of Alberta, Edmonton, Canada
  Master of Science in Computer Science
  Sep. 2023 – Jan. 2026
  GPA: 3.83 / 4.0

• Amirkabir University of Technology, Tehran, Iran
  Bachelor of Science in Computer Engineering
  Sep. 2018 – Jun. 2023
  GPA: 3.76 / 4.0

Experience

• Client Coaching (Startup Mentorship)
  Alberta Machine Intelligence Institute (Amii), Edmonton, Canada
  Jan. 2026 – Present

  • Advised startups on the design and architecture of LLM-based agent systems, from ideation to implementation

• Project Validation (Technical Advisement)
  Alberta Machine Intelligence Institute (Amii), Edmonton, Canada
  Jan. 2025 – Mar. 2025

  • Advised on designing an LLM-based RAG pipeline to assess contractor policy alignment with owner requirements
  • Proposed parameter-efficient fine-tuning and context engineering strategies for deployment-constrained settings
  • Guided model and system selection by balancing accuracy, latency, and cost trade-offs across the ML stack

• Natural Language Processing Research Scientist
  University of Alberta, Edmonton, Canada
  Jan. 2024 – Jan. 2026

  • Improved long-term memory and long-context reasoning in LLMs by up to 12.69% over strong baselines
  • Designing a severity-aware metric and model to quantify the harm of errors in LLM outputs
  • Built a medical RAG chatbot that improved accuracy, readability, comprehensiveness, and empathy over baselines by integrating multimodal retrieval, long-term memory, and hallucination detection
  • Built inference-time scaling and agentic AI systems to support multi-step reasoning in LLM applications

• Software Engineer
  Digikala, Tehran, Iran
  Jan. 2022 – May 2022

  • Reduced large-scale database query latency by 20% by optimizing query plans and indexing strategies in production systems
  • Developed a PHP (Symfony) service for generating diverse reports, significantly improving report delivery time
  • Built and deployed a highly efficient caching mechanism, reducing data retrieval latency by approximately 15%

• Backend Developer
  Narvan Startup Studio, Tehran, Iran
  Jun. 2021 – Jan. 2022

  • Enabled high-performance backend architecture using Nginx, gRPC, Elasticsearch, and PostgreSQL
  • Integrated monitoring tools such as Prometheus and Kafka to ensure optimal application performance

• Machine Learning Engineer & Frontend Developer
  Bookapo, Tehran, Iran
  Aug. 2020 – Jun. 2021

  • Developed machine learning models to recommend similar books, enhancing user engagement
  • Built the frontend of the Bookapo platform using React.js, delivering a seamless and intuitive user interface

• Computer Vision Research Scientist
  NODET, Tehran, Iran
  May 2020 – Dec. 2020

  • Developed object detection models for identifying diverse objects in aerial imagery
  • Designed and implemented image pre- and post-processing pipelines

Technical Skills

• Programming Languages: Python, C/C++, Java, Go
• Machine Learning & NLP: PyTorch, Hugging Face Transformers, LangChain, LlamaIndex, spaCy
• Agentic Systems: Tool-Using Agents, Multi-Agent Systems, Memory-Augmented Architectures
• Retrieval & Search: FAISS, Chroma, Milvus, Elasticsearch, RAG Pipelines, Knowledge Graphs
• Fine-Tuning & Optimization: PEFT, DeepSpeed, BitsAndBytes, Quantization
• Inference & Serving: vLLM, Ray Serve, Distributed Inference
• Databases: PostgreSQL, MongoDB
• MLOps & Infrastructure: Docker, Kubernetes, CI/CD, Git, Bash, Weights & Biases
• Cloud Platforms: AWS, GCP
• Web & App Development: Django, JavaScript, React, Node.js, Android

Publications

Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs

Mohammad Tavakoli, Alireza Salemi, Carrie Ye, Mohamed Abdalla, Hamed Zamani, J Ross Mitchell.

Semi-Automated Construction of Sense-Annotated Datasets for Practically Any Language

Jai Riley, Bradley M Hauer, Nafisa Sadaf Hriti, Guoqing Luo, Amir Reza Mirzaei, Ali Rafiei, Hadi Sheikhi, Mahvash Siavashpour, Mohammad Tavakoli, Ning Shi, Grzegorz Kondrak.

UAlberta at SemEval-2024 Task 1: A Potpourri of Methods for Quantifying Multilingual Semantic Textual Relatedness and Similarity

Ning Shi, Senyu Li, Guoqing Luo, Amirreza Mirzaei, Ali Rafiei, Jai Riley, Hadi Sheikhi, Mahvash Siavashpour, Mohammad Tavakoli, Bradley Hauer, Grzegorz Kondrak.