CV

AI Research Scientist

IQVIA

• Designed and trained transformer-based foundation models on longitudinal clinical data, enabling structured reasoning over long patient timelines.
• Developed agentic LLM systems for automated knowledge extraction and verification from large document collections using LangGraph and retrieval pipelines.

Postdoctoral Research Associate

University of Cambridge

• Secured a GBP 150k Foresight AI Safety grant to advance research on mechanistic machine unlearning and AI safety.
• Co-led a EUR 530k-funded research project on scalable decentralized LLM pre-training with privacy-preserving and robust training pipelines.
• Developed novel machine unlearning techniques for efficient and secure data removal, addressing regulatory requirements such as GDPR compliance.
• Designed and evaluated distributed LLM training systems using PyTorch, Transformers, and MosaicML in large-scale environments.
• Built scalable evaluation pipelines for LLM fine-tuning across downstream tasks, improving reproducibility and benchmarking.
• Published research in top-tier venues including NeurIPS and ICLR.

Graduate Research Assistant

University of Warwick

• Pioneered machine unlearning algorithms addressing data deletion and privacy requirements in large-scale ML systems.
• Designed a continual learning framework achieving more than 10x throughput improvement compared to prior approaches.
• Developed a machine unlearning algorithm outperforming prior state-of-the-art methods by up to 10 percent across benchmarks.
• Secured GBP 150k research funding from Huawei for machine learning-based database indexing systems.
• Led collaborations with Google DeepMind, including co-organizing the NeurIPS 2023 Machine Unlearning Challenge.
• Co-authored more than 7 publications in NeurIPS, SIGMOD, and CIDR.

Data Engineer

Iran Telecommunication Research Center (ITRC)

• Built an end-to-end big data pipeline from crawling to Hadoop and OLAP, reducing data onboarding time by 5x.
• Implemented scalable ETL workflows, achieving a 5x query speed-up.
• Integrated Elasticsearch with PowerBI dashboards, reducing reporting delays by 60 percent.

Machine Learning Engineer

Refah Retail Chain Stores Co.

• Led development and deployment of a real-time computer vision system for customer footfall analysis, achieving 81 percent accuracy across 20 stores.
• Developed in-store heatmap analytics to optimize staffing and store layout decisions.
• Built a multimodal recommendation system combining LSTM and CNN models, increasing customer engagement by 15 percent.
• Implemented time-series regression models for customer behavior prediction.

Deep Learning Engineer

Sensifai

• Improved production audio classification accuracy by 9 percent using multimodal transfer learning techniques.
• Built an 88 percent accurate music mood classifier using spectrogram-based CNN models.
• Optimized distributed video crawling pipelines, achieving 1.8x throughput.

PhD

University of Warwick

Computer Science

• Thesis: Adaptability of ML-Based Database Systems (SIGMOD Honorable Mention Award).
• Conducted the first study of data deletion in learned database systems (SIGMOD 2024).
• Developed SCRUB, a state-of-the-art unlearning algorithm for large-scale deep models (NeurIPS 2023).
• Proposed DDUp, a framework for efficient data insertion in learned database systems (SIGMOD 2023).
• Collaborated with Google DeepMind to launch the NeurIPS Machine Unlearning Challenge.

MSc

Tarbiat Modares University

Computer Science

• Dissertation: Hand Gesture Recognition Using 2D and 3D Convolutional Neural Networks from Video.
• GPA: 3.67/4.

BSc

Isfahan University of Technology

Computer Engineering

• GPA: 3.65/4.

Secured GBP 150k Foresight AI Safety Grant

NeurIPS Top Reviewer Recognition

SIGMOD Jim Gray Doctoral Dissertation Honorable Mention

EUR 530k SPRIN-D Grant

Co-lead, CambridgeFlower

Organizer, NeurIPS Machine Unlearning Workshop

Best Presentation Award, WPCCS, University of Warwick

Graduate Scholarship

GBP 25k per year, University of Warwick

Research Grant

GBP 15k per year, Huawei

DEPT: Decoupled Embeddings for Pre-training Language Models

ICLR

Top 1 percent paper on pre-training language models with decoupled embeddings.

Bridge the Gaps between Machine Unlearning and AI Regulation

NeurIPS

What Makes Unlearning Hard and What to Do About It

NeurIPS

Machine Unlearning in Learned Database Systems

SIGMOD

Towards Unbounded Machine Unlearning

NeurIPS

Detect, Distill and Update: Learned DB Systems Facing OOD Data

SIGMOD