CV

Download CV (PDF)

Education

• Ph.D. in Electrical and Computer Engineering, Georgia Institute of Technology, Sep 2023 – present
  • Advisor: Prof. Amirali Aghazadeh
  • Collaborative Specialization: Machine Learning and Digital Signal Processing
• M.S. in Electrical and Computer Engineering, Georgia Institute of Technology, 2026
  • Thesis: Hypothesis Generation from High-Dimensional Scientific Data Using Multi-Agent AI
• Technical AI Safety, BlueDot Impact, 2026
  • Cohort course on alignment and RLHF, mechanistic interpretability, evaluations and red-teaming, AI control, and scalable oversight
• B.S. in Computer Engineering, University of Tehran, Sep 2019 – Jun 2023
  • GPA: 17.98/20

Experience

• AI Safety Research Fellow, AI Safety Institute (AISI), Sep 2025
  • Research on AI safety and alignment — ensuring AI systems remain beneficial and controllable as they scale.
• Graduate Research Assistant, Georgia Institute of Technology, Sep 2023 – present
  • Deep-learning methods to reduce the cost of cryo-EM imaging for structural biology.
  • AI agents to accelerate scientific discovery and automate research workflows.
  • AI analysis of NASA astrobiological data to study the origin of life.
• Research Fellow, Fatima Fellowship, May 2022 – Dec 2022
  • Identified failure modes of SOTA debiasing techniques (SentDebias, INLP) in masked language modeling.
  • Built PyDebiaser, an open-source library of seven debiasing methods for Transformers.
• Founder, Jooyan, 2014 – 2016
  • Co-founded a startup helping companies hire programmers via coding challenges, plus an online course forum.

Publications

Autonomous Multi-Agent Reconstruction of Prebiotic Reaction Networks Reveals Organizational Features of Amino Acid Synthesis

D. Saeedi, N. Pokhrel, L. Gao, C. Wen, E. Bruce, J. C. Aponte, A. Stockton, A. Aghazadeh. (2026). "Autonomous Multi-Agent Reconstruction of Prebiotic Reaction Networks Reveals Organizational Features of Amino Acid Synthesis." Preprint.

Generative Priors for Cryo-EM Image Reconstruction

D. Saeedi*, Z. Shabeeb*, D. Tsui*, V. Jamali, A. Aghazadeh. (2026). "Generative Priors for Cryo-EM Image Reconstruction." ICML 2026 Workshop on Generative and Agentic AI for Biology (GenBio).

ProtoMech: Protein Circuit Tracing via Cross-layer Transcoders

D. Tsui, K. Talreja, D. Saeedi, A. Aghazadeh. (2026). "ProtoMech: Protein Circuit Tracing via Cross-layer Transcoders." ICML 2026 Workshop on Mechanistic Interpretability.

Circuit Tracing in Autoregressive Protein Language Models

D. Tsui, W. Deinzer, D. Saeedi, A. Aghazadeh. (2026). "Circuit Tracing in Autoregressive Protein Language Models." ICML 2026 Workshop on Mechanistic Interpretability.

Protein Circuit Tracing via Cross-layer Transcoders

D. Tsui, K. Talreja, D. Saeedi, A. Aghazadeh. (2026). "Protein Circuit Tracing via Cross-layer Transcoders." International Conference on Machine Learning (ICML).

cryoSENSE: Compressive Sensing Enables High-throughput Microscopy with Sparse and Generative Priors on the Protein Cryo-EM Image Manifold

D. Saeedi*, Z. Shabeeb*, D. Tsui*, V. Jamali, A. Aghazadeh. (2026). "cryoSENSE: Compressive Sensing Enables High-throughput Microscopy with Sparse and Generative Priors on the Protein Cryo-EM Image Manifold." IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Discriminating Abiotic and Biotic Organics in Meteorite and Terrestrial Samples Using Machine Learning on Mass Spectrometry Data

D. Saeedi, D. Buckner, T. Walton, J. C. Aponte, A. Aghazadeh. (2025). "Discriminating abiotic and biotic organics in meteorite and terrestrial samples using machine learning on mass spectrometry data." PNAS Nexus, 4(11), pgaf334.

GT-NLP at SemEval-2025 Task 11: EmoRationale — Evidence-Based Emotion Recognition via Retrieval-Augmented Generation

D. Saeedi, A. Kheirandish, S. Saeedi, H. Sahour, A. A. Panahi, I. Naeeni. (2025). "GT-NLP at SemEval-2025 Task 11: EmoRationale, Evidence-Based Emotion Recognition via Retrieval-Augmented Generation." SemEval-2025.

Challenges and Opportunities in Using Amino Acids to Decode Carbonaceous Chondrites and Asteroid Parent-Body Processes

J. C. Aponte, H. L. McLain, D. Saeedi, A. Aghazadeh, J. E. Elsila, D. P. Glavin, J. P. Dworkin. (2025). "Challenges and Opportunities in Using Amino Acids to Decode Carbonaceous Chondrites and Asteroid Parent-Body Processes." Astrobiology.

Machine Learning Analysis of Mass Spectrometry Data Can Differentiate Organic Distributions in Meteoritic and Terrestrial Geologic Samples

D. K. Buckner, D. Saeedi, T. Walton, J. C. Aponte, A. Aghazadeh. (2025). "Machine Learning Analysis of Mass Spectrometry Data Can Differentiate Organic Distributions in Meteoritic and Terrestrial Geologic Samples." 56th Lunar and Planetary Science Conference (LPSC), Abstract 2729.

AstroAgents: Agentic AI for Scientific Discovery

D. Saeedi, D. K. Buckner, J. C. Aponte, A. Aghazadeh. (2025). "AstroAgents: Agentic AI for Scientific Discovery." ICLR 2025 Workshop on Agentic AI for Science / AMS 2025 (Oral).

Effective Data Augmentation Methods for Multi-label Classification Language Understanding Tasks

D. Saeedi, A. Panahi, S. Saeedi, A. Fong. (2022). "Effective Data Augmentation Methods for Multi-label Classification Language Understanding Tasks." Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval).